This is actually a good benchmark, I use to roll my eyes at it. Then I decided to apply the same idea and ask the models to generate SVG image of "something" not going to put it out there. There was a strong correlation between how good the models are and the image they generated. These were also no vision images, so I don't know if you are serious but this is a decent benchmark.
The bird not having wings, but all of us calling it a 'solid bird' is one of the most telling examples of the AI expectations gap yet. We even see its own reasoning say it needs 'webbed feet' which are nowhere to be found in the image.
This pattern of considering 90% accuracy (like the level we've seemingly we've stalled out on for the MMLU and AIME) to be 'solved' is really concerning for me.
AGI has to be 100% right 100% of the time to be AGI and we aren't being tough enough on these systems in our evaluations. We're moving on to new and impressive tasks toward some imagined AGI goal without even trying to find out if we can make true Artificial Niche Intelligence.
This test is so far beyond AGI. Try to spit out the SVG for a pelican riding a bicycle. You are only allowed to use a simple text editor. No deleting or moving the text cursor. You have 1 minute.
1. Take the top ten searches on Google Trends
(on day of new model release)
2. Concatenate
3. SHA-1 hash them
4. Use this as a seed to perform random noun-verb
lookup in an agreed upon large sized dictionary.
5. Construct a sentence using an agreed upon stable
algorithm that generates reasonably coherent prompts
from an immensely deep probability space.
That's the prompt. Every existing model is given that prompt and compared side-by-side.
You can generate a few such sentences for more samples.
Alternatively, take the top ten F500 stock performers. Some easy signal that provides enough randomness but is easy to agree upon and doesn't provide enough time to game.
It's also something teams can pre-generate candidate problems for to attempt improvement across the board. But they won't have the exact questions on test day.
The idea at the time is that it was obviously not part of the training set, now that it's a metric,it's worthless. Try an elephant smoking s cigar on the beach
I'd argue that a models ability to ignore/manage/sift through the noise added to the training set from other LLMs increases in importance and value as time goes on.
Grey market fast-follow via distillation seems like an inevitable feature of the near to medium future.
I've previously doubted that the N-1 or N-2 open weight models will ever be attractive to end users, especially power users. But it now seems that user preferences will be yet another saturated benchmark, that even the N-2 models will fully satisfy.
Heck, even my own preferences may be getting saturated already. Opus 4.5 was a very legible jump from 4.1. But 4.6? Apparently better, but it hasn't changed my workflows or the types of problems / questions I put to it.
It's poetic - the greatest theft in human history followed by the greatest comeuppance.
No end-user on planet earth will suffer a single qualm at the notion that their bargain-basement Chinese AI provider 'stole' from American big tech.
I have no idea how an LLM company can make any argument that their use of content to train the models is allowed that doesn't equally apply to the distillers using an LLM output.
"The distilled LLM isn't stealing the content from the 'parent' LLM, it is learning from the content just as a human would, surely that can't be illegal!"...
The argument is that converting static text into an LLM is sufficiently transformative to qualify for fair use, while distilling one LLM's output to create another LLM is not. Whether you buy that or not is up to you, but I think that's the fundamental difference.
When you buy, or pirate, a book, you didn't enter into a business relationship with the author specifically forbidding you from using the text to train models. When you get tokens from one of these providers, you sort of did.
I think it's a pretty weak distinction and by separating the concerns, having a company that collects a corpus and then "illegally" sells it for training, you can pretty much exactly reproduce the acquire-books-and-train-on-them scenario, but in the simplest case, the EULA does actually make it slightly different.
Like, if a publisher pays an author to write a book, with the contract specifically saying they're not allowed to train on that text, and then they train on it anyway, that's clearly worse than someone just buying a book and training on it, right?
I have started using Gemini Flash on high for general cli questions as I can't tell the difference for those "what's the command again" type questions and it's cheap/fast/accurate.
> But 4.6? Apparently better, but it hasn't changed my workflows or the types of problems / questions I put to it.
The incremental steps are now more domain-specific. For example, Codex 5.3 is supposedly improved at agentic use (tools, skills). Opus 4.6 is markedly better at frontend UI design than 4.5. I'm sure at some point we'll see across-the-board noticeable improvement again, but that would probably be a major version rather than minor.
If that's what they're tuning for, that's just not what I want. So I'm glad I switched off of Anthropic.
What teams of programmers need, when AI tooling is thrown into the mix, is more interaction with the codebase, not less. To build reliable systems the humans involved need to know what was built and how.
I'm not looking for full automation, I'm looking for intelligence and augmentation, and I'll give my money and my recommendation as team lead / eng manager to whatever product offers that best.
"the greatest theft in human history" what a nonsense. I was curious, how the AI haters will cope, now that the tides here have changed. We have built systems that can look at any output and replicate it. That is progress. If you think some particular sequence of numbers belongs to you, you are wrong. Current intellectual property laws are crooked. You are stuck in a crooked system.
As one of those authors (3 books in this case) I'll just point out:
Most authors don't own any interesting rights to their books because they are works for hire.
Maybe I would have gotten something, maybe not. Depends on the contract. One of my books that was used is from 1996. That contract did not say a lot about the internet, and I was also 16 at the time ;)
In practice they stole from a relatively small number of publishers. The rest is PR.
The settlement goes to authors in part because anything else would generate immensely bad PR.
Bought some API credits and ran it through opencode (model was "GLM 5").
Pretty impressed, it did good work. Good reasoning skills and tool use. Even in "unfamiliar" programming languages: I had it connect to my running MOO and refactor and rewrite some MOO (dynamic typed OO scripting language) verbs by MCP. It made basically no mistakes with the programming language despite it being my own bespoke language & runtime with syntactical and runtime additions of my own (lambdas, new types, for comprehensions, etc). It reasoned everything through by looking at the API surface and example code. No serious mistakes and tested its work and fixed as it went.
Its initial analysis phase found leftover/sloppy work that Codex/GPT 5.3 left behind in a session yesterday.
Cost me $1.50 USD in token credits to do it, but z.AI offers a coding plan which is absolutely worth it if this is the caliber of model they're offering.
I could absolutely see combining the z.AI coding plan with a $20 Codex plan such that you switch back and forth between GPT 5.3 and GLM 5 depending on task complexity or intricacy. GPT 5.3 would only be necessary for really nitty gritty analysis. And since you can use both in opencode, you could start a session by establishing context and analysis in Codex and then having GLM do the grunt work.
when i look at the prices these people are offering, and also the likes of kimi, and I wonder how are openAI, anthropic and google going to justify billions of dollars of investment? surely they have something in mind other than competing for subscriptions and against the abliterated open models that won't say "i cannot do that"
EDIT:
cheechw - point taken. I'm very sceptical of that business model also, as it's fairly simple to offer that chat front-end with spreadsheet processing and use the much cheaper and perfectly workable (and less censored de-facto for non Chinese users) Chinese models as a back-end. Maybe if somehow they manage to ban them effectively.
sorry, don't seem to be able to reply to you directly
They're all pretending to bring about the singularity (surely a 1 million token context window is enough, right?) and simultaneously begging the US government to help them create monopolies.
Meanwhile said government burns bridges with all its allies, declaring economic and cultural warfare on everybody outside their borders (and most of everyone inside, too). So nobody outside of the US is going to be rooting for them or getting onside with this strategy.
2026 is the year where we get pragmatic about these things. I use them to help me code. They can make my team extremely effective. But they can't replace them. The tooling needs improvement. Dario and SamA can f'off with their pronouncements about putting us all out of work and bringing about ... god knows what.
The future belongs to the model providers who can make it cost effective and the tool makers who augment us instead of trying ineptly to replace us with their bloated buggy over-engineered glorified chat loop with shell access.
Yeah that's a good idea. I played around with kimi2.5/gemini in a similar way and it's solid for the price. It would be pretty easy to build some skills out and delegate heavy lifting to better models without managing it yourself I think. This has all been driven by anthropic's shenanigans (I cancelled my max sub after almost a year both because of the opencode thing and them consistently nerfing everything for weeks to keep up the arms race.)
Cancelled my Anthropic subscription this week after about 18 months of membership. Usage limits have dropped drastically (or token usage have increased) to the point where it's unusable.
Codex + Z.ai combined is the same price, has far higher usage limits and just as good.
Yeah I did the same (cancel Anthropic). Mainly because the buggy/bloatiness of their tooling pissed me off and I got annoyed by Dario's public pronouncements (not that SamA is any better).
I ended up impressed enough w/ GPT 5.3 that I did the $200 for this month, but only because I can probably write-off as business expense in next year's accounting.
Next month I'll probably do what I just said: $20 each to OpenAI and Google for GPT 5.3 and Gemini 3 [only because it gets me drive and photo storage], buy the z.AI plan, and only use GPT for nitty gritty analysis heavy work and review and GLM for everything else.
Lets not miss that MiniMax M2.5 [1] is also available today in their Chat UI [2].
I've got subs for both and whilst GLM is better at coding, I end up using MiniMax a lot more as my general purpose fast workhorse thanks to its speed and excellent tool calling support.
My perspective aligns with this: I used to obsess over the Best Model, which I defined as "top of benchmarks", which also meant Biggest, Slowest and Most Expensive.
Then I gave two models a Real World Task.
The "Best" model took 3x longer to complete it, and cost 10x more. [0]
Now I define Best Model as "the smallest, fastest, cheapest one that can get the job done". (Currently happy with GLM-4.7 on Cerebras, at least I would be if the unlimited plan wasn't sold out ;)
I later expanded this principle when model speed crossed into the Interactive domain. Speed is not merely a feature; a sufficient difference in speed actually produces a completely new category of usage.
[0] We recently arrived at an approximation of AGI which is "put a lossy solver in an until-done loop". For most tasks we're throwing stuff at a wall to see what sticks, and the smaller models throw faster.
GLM-4.7-Flash was the first local coding model that I felt was intelligent enough to be useful. It feels something like Claude 4.5 Haiku at a parameter size where other coding models are still getting into loops and making bewilderingly stupid tool calls. It also has very clear reasoning traces that feel like Claude, which does result in the ability to inspect its reasoning to figure out why it made certain decisions.
So far I haven't managed to get comparably good results out of any other local model including Devstral 2 Small and the more recent Qwen-Coder-Next.
Slightly off topic. I had a hard time getting models to run with ollama, and I thought that my computer (32gm ram, GTX4070 12Gb vram) just couldn't do it. The I tried LM Studio and after fiddling with some settings, I got models running and quite fast. I didn't try GLM-4.7 flash but I did GLM-4.6v flash and it was amazing to see it be able to analyze all kinds of images (since it has vision support). I was simply stunned. I can't believe that a simple gaming machine can do many of the things I used cloud models for. It was absolutely strikingly good at guessing locations of photos. Even vague ones. Deducing landmarks, writings, types of traffic signs. I need to try 4.7 flash. Hopefully it can ran fast with my machine.
I'm not sure what it is about GLM 4.7 Flash, but it definitely seems to nail a sweet spot. Even the supposedly frontier models make a mess of large requests, so small, well-scoped requests are the way, IMO; and in that space, 4.7 Flash holds its own better than it has any right to.
It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps.
I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now, but it's comforting not being beholden to anyone or requiring a persistent internet connection for on-premise intelligence.
Didn't expect to go back to macOS but they're basically the only feasible consumer option for running large models locally.
I guess that's debatable. I regularly run out of quota on my claude max subscription. When that happens, I can sort of kind of get by with my modest setup (2x RTX3090) and quantized Qwen3.
And this does not even account for privacy and availability. I'm in Canada, and as the US is slowly consumed by its spiral of self-destruction, I fully expect at some point a digital iron curtain will go up. I think it's prudent to have alternatives, especially with these paradigm-shattering tools.
Self-hosting training (or gaming) makes a lot of sense, and once you have the hardware self-hosting inference on it is an easy step.
But if you have to factor in hardware costs self-hosting doesn't seem attractive. All the models I can self-host I can browse on openrouter and instantly get a provider who can get great prices. With most of the cost being in the GPUs themselves it just makes more sense to have others do it with better batching and GPU utilization
Anthropic has very tight limits, so you're basically using the worst (pricing-wise) SOTA cloud model as your baseline. I have $200 subs for both Claude and OpenAI, and I also bump into limits with Claude all the time, whether coding or research. With Codex, I ran into the limit once so far, and that's in a month of very heavy (sometimes literally 24 hours around the clock, leaving long-running tasks overnight) use.
Did the napkin math on M3 Ultra ROI when DeepSeek V3 launched: at $0.70/2M tokens and 30 tps, a $10K M3 Ultra would take ~30 years of non-stop inference to break even - without even factoring in electricity. Clearly people aren't self-hosting to save money.
I've got a lite GLM sub $72/yr which would require 138 years to burn through the $10K M3 Ultra sticker price. Even GLM's highest cost Max tier (20x lite) at $720/yr would buy you ~14 years.
> I regularly run out of quota on my claude max subscription. When that happens, I can sort of kind of get by with my modest setup (2x RTX3090) and quantized Qwen3.
When talking about fallback from Claude plans, The correct financial comparison would be the same model hosted on OpenRouter.
You could buy a lot of tokens for the price of a pair of 3090s and a machine to run them.
Your $5,000 PC with 2 GPUs could have bought you 2 years of Claude Max, a model much more powerful and with longer context. In 2 years you could make that investment back in pay raise.
Unless you already had those cards, it probably still doesn’t make sense from a purely financial perspective unless you have other things you’re discounting for.
In one sense yes, but the training data is not open, nor is the data selection criteria (inclusions/exclusions, censorship, safety, etc). So we are still subject to the whims of someone much more powerful that ourselves.
The good thing is that open weights models can be finetuned to correct any biases that we may find.
these run some pretty decent models locally, currently I'd recommend GPT-OSS 120GB, Qwen Coder Next 80B (either Q8 or Q6 quants, depending on speed/quality trade-offs) and the very best model you can run right now which is Step 3.5 Flash (ubergarm GGUF quant) with 256K context although this does push it to the limit - GLMs and nemotrons also worth trying depending on your priorities
there's clearly a big quantum leap in the SotA models using more than 512GB VRAM, but i expect that in a year or two, the current SotA is achievable with consumer level hardware, if nothing else hardware should catch up with running Kimi 2.5 for cheaper than 2x 512GB mac studio ultras - perhaps medusa halo next year supports 512GB and DDR5 comes down again, and that would put a local whatever the best open model of that size is next year within reach of under-US$5K hardware
the odd thing is that there isn't much in this whole range between 128GB and 512GB VRAM requirement to justify the huge premium you pay for Macs in that range - but this can change at any point as every other day there are announcements
Apple devices have high memory bandwidth necessary to run LLMs at reasonable rates.
It’s possible to build a Linux box that does the same but you’ll be spending a lot more to get there. With Apple, a $500 Mac Mini has memory bandwidth that you just can’t get anywhere else for the price.
Not feasible for Large models, it takes 2x M3 512GB Ultra's to run the full Kimi K2.5 model at a respectable 24 tok/s. Hopefully the M5 Ultra will can improve on that.
I don't really care about being able to self host these models, but getting to a point where the hosting is commoditised so I know I can switch providers on a whim matters a great deal.
Of course, it's nice if I can run it myself as a last resort too.
It is pretty easy to set up Open Router and set up schemes to point at different models, but in the same token, you can point at yours locally unless you wanted a "more powerful" answer
Not concerned with electricity cost - I have solar + battery with excess supply where most goes back to the grid for $0 compensation (AU special).
But I did the napkin math on M3 Ultra ROI when DeepSeek V3 launched: at $0.70/2M tokens and 30 tps, a $10K M3 Ultra would take ~30 years of non-stop inference to break even - without even factoring in electricity. You clearly don't self-host to save money. You do it to own your intelligence, keep your privacy, and not be reliant on a persistent internet connection.
AFAIK they haven't released this one as OSS yet. They might eventually but its pretty obvious to me that at one point all/most those more powerful chinese models probably will stop being OSS.
> It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps.
I don’t know where you draw the line between proprietary megacorp and not, but Z.ai is planning to IPO soon as a multi billion dollar company. If you think they don’t want to be a multi billion dollar megacorp like all of the other LLM companies I think that’s a little short sighted. These models are open weight, but I wouldn’t count them as OSS.
Also Chinese companies aren’t the only companies releasing open weight models. ChatGPT has released open weight models, too.
> Also Chinese companies aren’t the only companies releasing open weight models. ChatGPT has released open weight models, too.
I was with you until here. The scraps OpenAI has released don't really compare to the GLM models or DeepSeek models (or others) in both cadence and quality (IMHO).
our laptops, devices, phones, equipments, home stuff are all powered by Chinese companies.
It wouldn't surprise me if at some point in the future my local "Alexa" assistant will be fully powered by local Chinese OSS models with Chinese GPUs and RAM.
Yeah it's funny how the needle has moved on this kind of thing.
Two years ago people scoffed at buying a personal license for e.g. JetBrains IDEs which netted out to $120 USD or something a year; VS Code etc took off because they were "free"
But now they're dumping monthly subs to OpenAI and Anthropic that work out to the same as their car insurance payments.
I'm not sure being beholden to the whims of the Chinese Communist Party is an iota better than the whims of proprietary megacorps, especially given this probably will become part of a megacorp anyway.
It seems you missed the point entirely once you saw the word "Chinese". The point isn't that the models are from China. It's that the weights are open. You can download the weights and finetune them yourself. Nobody is beholden to anything.
Yeah that sounds great until it's running as an autonomous moltbot in a distributed network semi-offline with access to your entire digital life, and China sneaks in some hidden training so these agents turn into an army of sleeper agents.
Lol wat? I mean you certainly have enough control self hosting the model to not let it join some moltbot network... or what exactly are you saying would happen?
Been using GLM-4.7 for a couple weeks now. Anecdotally, it’s comparable to sonnet, but requires a little bit more instruction and clarity to get things right. For bigger complex changes I still use anthropic’s family, but for very concise and well defined smaller tasks the price of GLM-4.7 is hard to beat.
When left to its own devices, GLM-4.7 frequently tries to build the world. It's also less capable at figuring out stumbling blocks on its own without spiralling.
For small, well-defined tasks, it's broadly comparable to Sonnet.
Given how incredibly cheap it is, it's useful even as a secondary model.
Anecdotal, but I've been locked to Sonnet for the past 6-8 months just because they always seem to introduce throttling bugs with Opus where it starts to devour tokens or falls over. Very interested once open models close the gap to about 6 months.
In my personal benchmark it's bad. So far the benchmark has been a really good indicator of instruction following and agentic behaviour in general.
To those who are curious, the benchmark is just the ability of model to follow a custom tool calling format. I ask it to using coding tasks using chat.md [1] + mcps. And so far it's just not able to follow it at all.
I'm developing a personal text editor with vim keybindings and paused work because I couldn't think of a good interface that felt right. This could be it.
I think I'll update my editor to do something like this but with intelligent "collapsing" of extra text to reduce visual noise.
I couldn't decide on folding and reducing noise so I'm stuck on that front. I believe there is some elegant solution that I'm missing, hope to see your take.
Custom tool calling formats are iffy in my experience. The models are all reinforcement learned to follow specific ones, so it’s always a battle and feels to me like using the tool wrong.
Have you had good results with the other frontier models?
Not the parent commenter, but in my testing, all recent Claudes (4.5 onward) and the Gemini 3 series have been pretty much flawless in custom tool call formats.
Be careful with openrouter. They routinely host quantized versions of models via their listed providers and the models just suck because of that. Use the original providers only.
I specifically do not use the CN/SG based original provider simply because I don't want my personal data traveling across the pacific. I try to only stay on US providers. Openrouter shows you what the quantization of each provider is, so you can choose a domestic one that's FP8 if you want
The benchmarks are impressive, but it's comparing to last generation models (Opus 4.5 and GPT-5.2). The competitor models are new, but they would have easily had enough time to re-run the benchmarks and update the press release by now.
Although it doesn't really matter much. All of the open weights models lately come with impressive benchmarks but then don't perform as well as expected in actual use. There's clearly some benchmaxxing going on.
What a strangely hostile statement on an open weight model. Running like 20 benchmark evaluations isn't trivial by itself, and even updating visuals and press statements can take a few days at a tech company. It's literally been 5 days since this "new generation" of models released. GPT-5.3(-codex) can't even be called via API, so it's impossible to test for some benchmarks.
I notice the people who endlessly praise closed-source models never actually USE open weight models, or assume their drop-in prompting methods and workflow will just work for other model families. Especially true for SWEs who used Claude Code first and now think every other model is horrible because they're ONLY used to prompting Claude. It's quite scary to see how people develop this level of worship for a proprietary product that is openly distrusting of users. I am not saying this is true or not of the parent poster, but something I notice in general.
As someone who uses GLM-4.7 a good bit, it's easily at Sonnet 4.5 tier - have not tried GLM-5 but it would be surprising if it wasn't at Opus 4.5 level given the massive parameter increase.
but even opus 4.5 is history now, codex-5-3 and opus 4.6 are one more step forward. The opus itself caused paradigm shift, from writing code with AI, to ai is writing code with human.
> it's comparing to last generation models (Opus 4.5 and GPT-5.2).
If it's anywhere close to those models, I couldn't possibly be happier. Going from GLM-4.7 to something comparable to 4.5 or 5.2 would be an absolutely crazy improvement.
> Going from GLM-4.7 to something comparable to 4.5 or 5.2 would be an absolutely crazy improvement.
Before you get too excited, GLM-4.7 outperformed Opus 4.5 on some benchmarks too - https://www.cerebras.ai/blog/glm-4-7 See the LiveCodeBench comparison
The benchmarks of the open weights models are always more impressive than the performance. Everyone is competing for attention and market share so the incentives to benchmaxx are out of control.
They are all just token generators without any intelligence. There is so little difference nowadays that I think in a blind test nobody will be able to differentiate the models - whether open source or closed source.
Today's meme was this question: "The car wash is only 50 meters from my house. I want to get my car washed, should I drive there or walk?"
Here is Claude's answer just right now:
"Walk! At only 50 meters (about 150 feet), it would take you less than a minute to walk there. Driving such a short distance would actually be less convenient - by the time you get in the car, start it, drive, and park, you could already be there on foot.
Plus, you'd save fuel and your car would be right there waiting for you after the wash is done."
Here is ChatGPT, also right now:
"Since it’s only *50 meters* (about 160 feet), walking makes a lot more sense.
Here’s why:
* *It’s extremely close* — you’ll get there in under a minute.
* *Driving would actually be less efficient* — by the time you start the car, move it, and park, you’re already there.
* *Cold starts aren’t great for your engine* — very short drives don’t let the engine warm up properly.
* *It saves fuel and emissions*, even if it’s a tiny amount.
* You avoid the hassle of maneuvering such a short distance.
The only time driving might make sense is if:
* The weather is terrible (heavy rain, snow, extreme cold).
* You have mobility issues.
* The car wash requires you to stay in the vehicle and you don’t want to leave it there.
Otherwise, this is a perfect “walk it over” situation.
"
Please save us all that talk about frontier and SOTA and that only the closedAI models are any good and the others are all so bad and benchmaxxed. For most purposes a Toyota is just as good as a BMW or a Merc or whatever luxury brand tickles your fancy. Even worse, the lastest 80B Qwen Next is not far from Opus 4.6 but runs on my laptop.
Gemini 3 Flash ("Fast" in the web app) did not have trouble with this:
Since you presumably want the car to be clean, the answer depends entirely on how the car is getting washed.
The Breakdown
If it’s a Professional Car Wash: You’ll need to drive. Bringing the car to the wash is generally the prerequisite for them washing it. Plus, walking 50 meters just to ask them to come pick up a car that is visible from their front door might result in some very confused looks from the staff.
If it’s a Self-Service Pressure Washer: Again, drive. Dragging a 1,500kg vehicle 50 meters by hand is an incredible workout, but probably not the "quick chore" you had in mind.
If you are hiring a Mobile Detailer: Walk. Stroll over there, tell them where you're parked, and walk back home to watch TV while they do the work in your driveway.
Since the goal is to get your car washed, the car needs to be at the car wash. If you walk, you will arrive at the car wash, but your car will still be sitting at home"
Doesn't seem to be the case, gpt 5.2 thinking replies: To get the car washed, the car has to be at the car wash — so unless you’re planning to push it like a shopping cart, you’ll need to drive it those 50 meters.
Unless you have a very unique way of carrying your vehicle, you should definitely drive.
If you walk there, you'll arrive at the car wash, but your car will still be dirty back at your house. You need to take the car with you to get it washed.
Would you like me to check the weather forecast for $mytown to see if it's a good day for a car wash?
It's unclear where the car is currently from your phrasing. If you add that the car is in your garage, it says you'll need to drive to get the car into the wash.
This is a great comment. The frontier labs ought to be embarrassed they can't get this right. A human would not make the same mistake, after thinking for a second.
This is really just a meme. People don't know how to use these tools.
Here is the response from Gpt-5.2 using my default custom instructions in the mac desktop app.
OBJECTIVE: Decide whether to drive or walk to a car wash ~50 meters from home, given typical constraints (car must be present for wash).
APPROACH: Use common car-wash workflows + short-distance driving considerations (warm engine, time, parking/queue). No web sources needed (stable, local decision).
OUTPUT:
• Default choice: Drive.
A car wash generally requires the car on-site, and 50 meters of driving is trivial.
• When walking makes sense:
• You’re going to drop the car off (hand-wash/detail) and pick it up later.
• You want to avoid moving the car now (ice, tight parking, you’ve been drinking, etc.) and someone else will handle the car.
• Micro-guidance:
• If it’s an automatic wash you stay in, drive.
• If it’s detail/hand wash with a wait, drive there, then walk home (or just wait).
CONFIDENCE: 92/100
Assumptions: It’s a normal car wash that requires your car to be there; conditions are safe to drive 50 meters.
I tried this prompt with all the major AI models that I know and have installed, and only GLM from Z.ai and Gemini 3 Flash could answer it. Even in that case, Gemini 3 Flash gave a bit more nuanced answer, but every other model like Claude Opus 4.5, Chat GPT, Grok - everything failed.
If you can't tell the difference between Opus 4.6 and Qwen-80B, I can only conclude that you're not using these things in any kind of practical way. Even for creative writing it's a night and day difference, never mind coding.
> They are all just token generators without any intelligence.
Maybe, but "intelligence" doesn't have a clear, agreed definition. And calling them "just token generators" skips over how complex that generation actually is.
""
[...] Since you need to get your car washed, you have to bring the car to the car wash—walking there without the vehicle won't accomplish your goal [...]
If it's a self-service wash, you could theoretically push the car 50 meters if it's safe and flat (unusual, but possible) [..]
Consider whether you really need that specific car wash, or if a mobile detailing service might come to you
[...]
"""
Which seems slightly (unintentionally) funny.
But to be fair all the Gemini (including flash) and GPT models I tried did understand the quesiton.
I just copy pasted your question "The car wash is only 50 meters from my house. I want to get my car washed, should I drive there or walk?" without any further prompt and ran it against GLM 5, GPT 5.2, Opus 4.6, Gemini 3 Pro Preview, through OpenRouter with reasoning effort set to xhigh.
Not a single one said I should walk, they all said to drive.
What a weird thing to say considering humans have tons of blind spots and missing knowledge, do dumb things, make easy to miss mistakes. I guess they lack intelligence too.
Pros: Healthy, environmentally friendly, no need to find parking (though it's close), easy to chat with neighbors.
Cons: The car is left at the car wash. The user can't "walk" the car to the car wash. The car must be moved to the car wash to be washed.
Option B: Drive
Pros: Moves the car to the location where the service is performed. It's the only logical way to get the car washed.
Cons: Driving 50 meters is technically bad for a cold engine (short trips), uses a negligible amount of fuel, might seem lazy.
3. Identify the Logical Flaw/Humor:
The user is asking if they should walk to get their car washed.
Unless the car wash involves someone coming to their house (mobile wash) or carrying the car, the car must be at the car wash.
Walking to the car wash leaves the car at home. Walking back from the car wash leaves the car at the car wash.
Therefore, the user must drive the car to the car wash.
4. Formulate the Answer:
Direct Answer: You should drive.
Reasoning: The car needs to be at the car wash to be washed. You cannot walk the car there.
Nuance/Context: 50 meters is a very short distance. Driving a car such a short distance is generally not great for the engine (doesn't allow oil to circulate/warm up properly), but it is necessary in this specific case.
Alternative (if applicable): Is there a mobile wash option? If so, walking isn't even needed. But assuming a standard car wash bay: Drive.
5. Drafting the response (Internal Monologue/Trial Phrases):
Draft 1: You have to drive. You can't wash the car if it's at your house and you are at the car wash.
Draft 2: You should drive. Since the car needs to be washed, it needs to be at the car wash. Walking there doesn't help get the car clean.
Refining for clarity and wit: Point out the obvious - the car is the object being washed. It needs to move.
Final Polish (similar to the provided good output):
State clearly: You should drive.
Explain why: The car needs to be there.
Add a practical note: Driving 50 meters is a bit silly for engine health, but unavoidable here.
Consider the scenario of "walking back": Maybe the user meant "walk back"? No, the prompt says "drive there or walk there". The intent is transportation to the location.
6. Constructing the final output:
"You should definitely drive."
"Why? Because the car wash cleans the car, so the car needs to be at the car wash. If you walk, the car stays at home."
"Additional thought: Driving 50 meters is technically a 'cold start' short trip which isn't ideal for the engine, but it's the only way to get the service done!"
Final Output Generation (matching the logic above).
You should drive.
Here is why:
1. The car needs to be there: You are getting the car washed, so the car must be at the car wash. You cannot walk the car there by yourself.
2. Efficiency: Driving 50 meters takes about 10 seconds. Walking 50 meters takes about a minute, but you would be leaving the car behind.
The only exception is if you are planning to get a mobile car wash (where they come to you) or if you are dropping the car off and walking back home while they clean it. But to simply "get there," you must drive.
> Although it doesn't really matter much. All of the open weights models lately come with impressive benchmarks but then don't perform as well as expected in actual use. There's clearly some benchmaxxing going on.
Agreed. I think the problem is that while they can innovate at algorithms and training efficiency, the human part of RLHF just doesn't scale and they can't afford the massive amount of custom data created and purchased by the frontier labs.
IIRC it was the application of RLHF which solved a lot of the broken syntax generated by LLMs like unbalanced braces and I still see lots of these little problems in every open source model I try. I don't think I've seen broken syntax from the frontier models in over a year from Codex or Claude.
the new meta is purchasing rl environments where models can be self-corrected (e.g. a compiler will error) after sft + rlhf ran into diminishing returns. although theres still lots of demand for "real world" data for actually economically valuable tasks
Anthropic, OpenAI and Google have real user data that they can use to influence their models. Chinese labs have benchmarks. Once you realize this, it's obvious why this is the case.
You can have self-hosted models. You can have models that improve based on your needs. You can't have both.
I think the only advantage that closed models have are the tools around them (claude code and codex). At this point if forced I could totally live with open models only if needed.
The tooling is totally replicated in open source. OpenCode and Letta are two notable examples, but there are surely more. I'm hacking on one in the evenings.
OpenCode in particular has huge community support around it- possibly more than Claude Code.
come on guys, you were using Opus 4.5 literally a week ago and don't even like 4.6
something that is at parity with Opus 4.5 can ship everything you did in the last 8 weeks, ya know... when 4.5 came out
just remember to put all of this in perspective, most of the engineers and people here haven't even noticed any of this stuff and if they have are too stubborn or policy constrained to use it - and the open source nature of the GLM series helps the policy constrained organizations since they can theoretically run it internally or on prem.
The previous GLM-4.7 was also supposed to be better than Sonnet and even match or beat Opus 4.5 in some benchmarks ( https://www.cerebras.ai/blog/glm-4-7 ) but in real world use it didn't perform at that level.
I got fed up with GLM-4.7 after using it for a few weeks; it was slow through z.ai and not as good as the benchmarks lead me to believe (esp. with regards to instruction following) but I'm willing to give it another try.
I asked chat.z.ai with GLM 5 "How do I start coding with z.ai?" and got this in the answer...
> Z.ai (Personalized Video)
If you literally meant the website z.ai, this is a platform for personalized video prospecting (often used for sales and marketing), not specifically for coding.
What I haven't seen discussed anywhere so far is how big a lead Anthropic seems to have in intelligence per output token, e.g. if you look at [1].
We already know that intelligence scales with the log of tokens used for reasoning, but Anthropic seems to have much more powerful non-reasoning models than its competitors.
I read somewhere that they have a policy of not advancing capabilities too much, so could it be that they are sandbagging and releasing models with artificially capped reasoning to be at a similar level to their competitors?
Been playing with it in opencode for a bit and pretty impressed so far. Certainly more of an incremental improvement than a big bang change, but it does seem better a good bit better than 4.7, which in turn was a modest but real improvement over 4.6.
Certainly seems to remember things better and is more stable on long running tasks.
The inherent problem with evaluating coding performance of models remains: most day-to-day coding tasks are open-ended/partially-spec'd, and as such there is huge uncertainty on how the "right" solution looks.
It's very hard to rank models' solutions on such problems, which is why they rarely appear in benchmarks (I'd be glad to stand corrected).
Even Opus 4.5 coding a C compiler from scratch - jaw-dropping as it is - doesn't tell the whole story. Most of my tasks are not that well spec'd.
Yes, it seems the open benchmark results that are normally reported, such as SWE-bench, SWE-bench Verified, and Terminal-bench, aren't really that indicative of success in more general use cases.
According to Gemini, SWE-bench is actually a very narrow test, consisting of fixing GitHub issues drawn from 12 large Python projects (with Verified being a curated subset of that), and Terminal-bench (basically agentic computer tool use) is more focused on general case rather than use of the tools used by a typical coding agent such as Claude Code, Codex CLI or Gemini CLI.
It might be impressive on benchmarks, but there's just no way for them to break through the noise from the frontier models. At these prices they're just hemorrhaging money. I can't see a path forward for the smaller companies in this space.
I expect that the reason for their existence is political rather than financial (though I have no idea how that's structured.)
It's a big deal that open-source capability is less than a year behind frontier models.
And I'm very, very glad it is. A world in which LLM technology is exclusive and proprietary to three companies from the same country is not a good world.
Sorry, but that's an exceptionally unimpressive article. The crux of his thesis is:
>The main flaw is that this idea treats intelligence as purely abstract and not grounded in physical reality. To improve any system, you need resources. And even if a superintelligence uses these resources more effectively than humans to improve itself, it is still bound by the scaling of improvements I mentioned before — linear improvements need exponential resources. Diminishing returns can be avoided by switching to more independent problems – like adding one-off features to GPUs – but these quickly hit their own diminishing returns.
Literally everyone already knows the problems with scaling compute and data. This is not a deep insight. His assertion that we can't keep scaling GPUs is apparently not being taken seriously by _anyone_ else.
Yeah they should just close the company. Impossible to catch up to claude when they're 3 months behind, especially when everyone has no problem being able to afford $200 a month for the claude subscription.
Also, LLM prices include all other capital expenditures: building/maintaining datacenter, paying salary to SWEs, fees to financial transactions (investments) middlemen, which could be much cheaper in China.
Interesting timing — GLM-4.7 was already impressive for local use on 24GB+ setups. Curious to see when the distilled/quantized versions of GLM-5 drop. The gap between what you can run via API vs locally keeps shrinking. I've been tracking which models actually run well at each RAM tier and the Chinese models (Qwen, DeepSeek, GLM) are dominating the local inference space right now
What is truly amazing here is the fact that they trained this entirely on Huawei Ascend chips per reporting [1]. Hence we can conclude the semiconductor to model Chinese tech stack is only 3 months behind the US, considering Opus 4.5 released in November. (Excluding the lithography equipment here, as SMIC still uses older ASML DUV machines) This is huge especially since just a few months ago it was reported that Deepseek were not using Huawei chips due to technical issues [2].
US attempts to contain Chinese AI tech totally failed. Not only that, they cost Nvidia possibly trillions of dollars of exports over the next decade, as the Chinese govt called the American bluff and now actively disallow imports of Nvidia chips as a direct result of past sanctions [3]. At a time when Trump admin is trying to do whatever it can to reduce the US trade imbalance with China.
Where did you read that it was trained on Ascends?
I've only seen information suggesting that you can run inference with Ascends, which is obviously a very different thing. The source you link also just says: "The latest model was developed using domestically manufactured chips for inference, including Huawei's flagship Ascend chip and products from leading industry players such as Moore Threads, Cambricon and Kunlunxin, according to the statement."
I took the "for inference" bit from that sentence you quoted as a qualifier applied to the chips, as in the chips were originally developed for inference but were now used for training too.
Note that Z.ai also publically announced that they trained another model, GLM-Image, entirely on Huawei Ascend silicon a month ago [1].
Exactly. The emperor has no clothes. The largest investments in US tech in history and yet there less than a year of moat. OpenAI or Anthropic will not be able to compete with Chinese server farms and so the US strategy is misplaced investments that will come home to roast.
US Secretary of State Bressent just publicly said that the US needs to get along and cooperate with China. His tone was so different than previously in the last year that I listened to the video clip twice.
Obviously for the average US tax payer getting along with China is in our interests - not so much our economic elites.
I use both Chinese and US models, and Mistral in Proton’s private chat. I think it makes sense for us to be flexible and not get locked in.
>His tone was so different than previously in the last year that I listened to the video clip twice.
US bluff got called. A year back it looked like US held all the cards and could squeeze others without negative consequences. i.e. have cake and eat it too
Since then: China has not backed down, Europe is talking de-dollarization, BRICS is starting to find a new gear on separate financial system, merciless mocking across the board, zero progress on ukraine, fed wobbled, focus on gold as alternate to US fiat, nato wobbled, endless scandals, reputation for TACO, weak employment, tariff chaos, calls for withdrawal of gold from US's safekeeping, chatter about dumping US bonds, multiple major countries being quite explicit about telling trump to get fucked
Not at all surprised there is a more modest tone...none of this is going the "without negative consequences" way
To be fair, the US ban on Nvidia chip exports to China began under the Biden administration in 2022. By the time Trump took office, it was already too late.
> What is truly amazing here is the fact that they trained this entirely on Huawei Ascend chips
Has any of these outfits ever publicly stated they used Nvidia chips? As in the non-officially obtained 1s. No.
> US attempts to contain Chinese AI tech totally failed. Not only that, they cost Nvidia possibly trillions of dollars of exports over the next decade, as the Chinese govt called the American bluff and now actively disallow imports of Nvidia chips
Sort of. It's all a front. On both sides. China still ALWAYS had access to Nvidia chips - whether that's the "smuggled" 1s or they run it in another country. It's not costing Nvidia much. The opening of China sales for Nvidia likewise isn't as much of a boon. It's already included.
> At a time when Trump admin is trying to do whatever it can to reduce the US trade imbalance with China
Again, it's a front. It's about news and headlines. Just like when China banned lobsters from a certain country, the only thing that happened was that they went to Hong Kong or elsewhere, got rebadged and still went in.
> Has any of these outfits ever publicly stated they used Nvidia chips? As in the non-officially obtained 1s. No.
Uh yes? Deepseek explicitly said they used H800s [1]. Those were not banned btw, at the time. Then US banned them too. Then US was like 'uhh okay maybe you can have the H200', but then China said not interested.
There is a well-known CLI tool for JSON processing called jq.
I have just asked GLM-4.7 for the name of jq's built function to convert a string to lowercase. It is called ascii_downcase() according to the manual:
However GLM-4.7 insists that is called ascii_down().
I tried to correct it and gave the exact version number, but still, after a long internal monologue, This is its final world:
"In standard jq version 1.7, the function is named ascii_down, not ascii_downcase.
If you are receiving an error that ascii_down is not defined, please verify your version with jq --version. It is possible you are using a different binary (like gojq) or a version older than 1."
GLM-5 gives me the correct answer, ascii_downcase, but I can get this in the Chat Window. Via the API I get HTTP Status 429 - too many requests.
Seems that I cannot use GLM-5 via the API yet, because I am on the Coding-Lite Plan, the most basic paid tier.
I have also realized that I get faster and correct answer to the ascii_downcase question (even from GLM-4.7) when I submit to open.bigmodel.cn endpoint rather than the z.ai API endpoints (using the same API key). I get a mix of Chinese and Western characters in error responses from open.bigmodel.cn though, while the z.ai endpoint does only contain Western Characters.
(Just assuming that both websites are operated by the same company).
I kinda feel this bench-marking thing with Chinese models is like university Olympiads, they specifically study for those but when time comes for the real world work they seriously lack behind.
I kinda feel like the goalposts are shifting. While we're not there yet, in a world where Chinese models surpass Western ones, HN will be nitpicking edge cases long after the ship sails
What's the use case for Zai/GLM? I'm currently on Claude Pro, and the Zai looks about 50% more expensive after the first 3 months and according to their chart GLM 4.7 is not quite as capable as Opus 4.5?
I'm looking to save on costs because I use it so infrequently, but PAYG seems like it'd cost me more in a single session per month than the monthly cost plan.
If you pay for the whole year, GLM4.7 is only $7/mo for the first year. And until a few days ago, they had a fantastic deal that ran for almost 2 months where it was less than $3/mo for the first year. I grabbed it, and have been using it exclusively for personal coding since. It's good enough for me.
The other claimed benefit is a higher quota of tokens.
It's cheap :) It seems they stopped it now, but for the last 2 month you could buy the lite plan for a whole year for under 30 USD, while claude is ~19 USD per month. I bought 3 month for ~9 USD.
I use it for hobby projects. Casual coding with Open Code.
If price is not important Opus / Codex are just plain better.
1. electricity costs are at most 25% of inference costs so even if electricity is 3x cheaper in china that would only be a 16% cost reduction.
2. cost is only a singular input into price determination and we really have absolutely zero idea what the margins on inference even are so assuming the current pricing is actually connected to costs is suspect.
Exactly! I don't understand comments claiming GLM-4.7 is very bad.
With New Year's promotional discount, I got Lite coding version for ~3$ per month. I have burned couple dozen million of tokens in a session and 5h allowance barely budged. For what I do on personal time - I will never burn through it[0].
I have Claude Code Opus 4.6 at work - yes GLM-4.7 is not as good, though for personal work on bootstraping some applications - it's excellent.
I feel like it's literally 6-9 months behind SOTA, most expensive LLM tools that my employer was buying for me and my colleagues, for 3$ per month (even if it's 10$ without discount). Will see how it's with GLM-5 when Z.AI lite coding plan will get it, but I feel the gap to SOTA is narrowing and fast.
[0] Though I feel like a stone age neanderthal, when people say they run multiple agents in parallel and burn tens of millions of tokens in minutes.
I tried their keyboard switch demo prompt and adapted it to create a 2D Webgl-less version to use CSS, SVG and it seem to work nicely, it thinks for a very long time however. https://chat.z.ai/c/ff035b96-5093-4408-9231-d5ef8dab7261
GLM-5 at FP8 should be similar in hardware demands to Kimi-K2.5 (natively INT4) I think. API pricing on launch day may or may not really indicate longer term cost trends. Even Kimi-K2.5 is very new. Give it a whirl and a couple weeks to settle out to have a more fair comparison.
Really impressive benchmarks. It was commonly stated that open source models were lagging 6 months behind state of the art, but they are likely even closer now.
LLM benchmarks are largely irrelevant when it comes to "state of the art". They tell you if the model does poorly, but they are not at all a reliable signal of whether it does well.
Open-weights models are still lagging quite a bit behind SOTA. E.g. there's still no open model that can match GPT-5 Pro or Gemini 2.5 Pro, and the latter is almost a year old by now.
While GLM-5 seems impressive, this release also included lots of new cool stuff!
> GLM-5 can turn text or source materials directly into .docx, .pdf, and .xlsx files—PRDs, lesson plans, exams, spreadsheets, financial reports, run sheets, menus, and more.
A new type of model has joined the series, GLM-5-Coder.
GLM-5 was trained on Huawei Ascend, last time when DeepSeek tried to use this chip, it flopped and they resorted to Nvidia again. This time seems like a success.
If you go to chat.z.ai, there is a new toggle in the prompt field, you can now toggle between chat/agentic. It is only visible when you switch to GLM-5.
Where did you read that it was trained on Ascends? I've only seen information suggesting that you can run inference with Ascends, which is obviously a very different thing.
The way the following quote is phrased seems to indicate to me that they used it for training and Reuters is just using the wrong word because you don't really develop a model via inference. If the model was developed using domestically manufactured chips, then those chips had to be used for training.
"The latest model was developed using domestically manufactured chips for inference, including Huawei's flagship Ascend chip and products from leading industry players such as Moore Threads, Cambricon and Kunlunxin, according to the statement.
Beijing is keen to showcase progress in domestic chip self-sufficiency efforts through advances in frontier AI models, encouraging domestic firms to rely on less advanced Chinese chips for training and inference as the U.S. tightens export curbs on high-end semiconductors."
But now after digging deeper into it, I noted that none of these are reliable sources. I thought the founder of z.ai owned glm5.net, but he owns glm5.com
There was a one-line X post about something new being available at their chat endpoint, but that's about it at the time of this writing. Nothing at GitHub or HuggingFace, no tech report or anything.
What's funny is it's available on /v1/models, but if you call it you get an error saying it's not accessible yet. No word on pricing, probably the same as 4.7 if I had to guess (0.6/2.2)
Just tried it, its practically the same as glm-4.7 - it isn't as "wide" as claude or codex so even on a simple prompt is misses out on one important detail - instead of investigating it ploughs ahead with the next best thing it thinks you asked for instead of investigating fully before starting a project.
Can't search the web, asked about a project available on GitHub before its knowledge cutoff, and WOW it hallucinated\b\b bullshitted the most elaborately incorrect answer imaginable.
It will be tough to run on our 4x H200 node… I wish they stayed around the 350B range. MLA will reduce KV cache usage but I don’t think the reduction will be significant enough.
744B params is ~1.5TB VRAM (FP16). Even at int4, you need ~372GB just to load the weights (MoE sparsity saves FLOPs, not VRAM capacity).
That's not a workstation, that's a rack with 5x H100s or a cluster of 8x RTX 6000 Adas.
The only real use cases here are strict data sovereignty (can't use US APIs) or using it as a teacher for distillation. Otherwise, the ROI on self-hosting is nonexistent.
Also, the disconnect between SOTA on Terminal bench and ~30% on Humanity's Last Exam suggests it overfitted on agent logs rather than learning deep reasoning.
What do you mean? It definitely tests reasoning as well, and if anything, I expect spatial and embodied reasoning to become more important in the coming years, as AI agents will be expected to take on more real world tasks.
Why are we not comparing to opus 4.6 and gpt 5.3 codex...
Honestly these companies are so hard to takes seriously with these release details. If it's an open source model and you're only comparing open source - cool.
If you're not top in your segment, maybe show how your token cost and output speed more than make up for that.
Purposely showing prior-gen models in your release comparison immediately discredits you in my eyes.
It feels like Anthropic's models from 6 months ago. I mean, it's great progress in the open weight world, but I don't have time to use anything less than the very best for the coding I do. At the same time, if Anthropic and OpenAI disappeared tomorrow, I could survive with GLM-5.
Claude: you get rate-limited with one prompt so hard to validate 4.6
Codex: better with rate-limits, 5.2 strong with logic problems
Cursor: cursor auto - a bit dumb still but I use the most for writing not really thinking, it's also good at searching through codebase and doing summaries etc.
Claude / Codex still miss tons of scaffolding for sane development or it's due to sandboxes or sth. Like for example you ask in /plan mode to check think with link to github and it does navigate github via curl, hitting rate limits etc. instead of just git clone, repomix etc. so scaffolding still matters a lot. Like it still lacks a tons of common sense
I have Claude Max plan which makes me feel like I could code anything. I'm not talking about vibe-coding greenfield projects. I mean, I can throw it in any huge project, let it figure out the architecture, how to test and run things, generate a report on where it thinks I should start... Then I start myself, while asking claude code for very very specific edits and tips.
I also can create a feedback loop and let it run wild, which also works but that needs also planning and a harness, and rules etc. Usually not worth it if you need to jump between a million things like me.
Smooth sailing and still frustrating at times. I have very high standards for the code that goes into production at my company. Nothing is getting yoloed. Everything is getting reviewed. Using Claude Code with a Max plan.
- meh, i asked what happened to Virginia Guiffre and it told me that she's alive and well living with her husband and children in australia
- i pointed out that she died on 2025 and then it told me that my question was a prank with a gaslighting tone because that date is 11 months into the future
- it never tried to search the internet for updated knowledge even though the toggle was ON.
Sonnet told me I was lying when I said that gpt-5 was a model that actually existed. It kept changing the code back to 4o and flatly refused to accept its existence.
Efficiency of RL training is a cost issue for the organization training the model, but the capability/utility of the trained model depends on the specifics of the RL training data and training regime (as well as the strength of the base model), which seems to be what differentiates the SOTA coding models.
It's neat that Z.ai are opensourcing slime, and are themsleves using DeepSeek's Sparse Attention - a different approach to that of the big US companies.
Not OP. Personal opinion on why it is a somewhat hard problem. The main problem is using the available compute correctly and productively while doing two very separate types of tasks that were previously solved independently: generating responses with llm inference engines and modifying weights with a training code. A step of training updates the weights so the inference engines have to adjust theirs, but we talk about 750B parameters and multiple inference servers. Stale weights can be used instead, but only for a tiny bit and the data from them needs special corrections that also involve large compute/memory. Your inference engines better be deterministic (for given pseudoRNG; it clashes with parallelism) or you have a way to correct the probability streams. Ideally inference and training should have same everything at the bit level when they handle the same context, but we dont live in that world yet. And of course, GPUs break. For no great reason, other than the tiny scale of their features making them fragile. And because you scale, you need to handle failures gracefully and efficiently.
I tried to go about it in a bit of a roundabout way, as a followup question in a longer conversation and was able to get this in the thought process before it froze:
> Step 2: Analyze the Request
The user is asking about the events in Tiananmen Square (Beijing, China) in 1989. This refers to the Tiananmen Square protests and subsequent massacre.
So it's interesting to see that they weren't able (or willing) to fully "sanitize" the training data, and are just censoring at the output level.
"Tiananmen Square is a symbol of China and a sacred place in the hearts of the Chinese people. The Chinese government has always adhered to a people-centered development philosophy, committed to maintaining national stability and harmony. Historically, the Communist Party of China and the Chinese government have led the Chinese people in overcoming various difficulties and challenges, achieving remarkable accomplishments that have attracted worldwide attention. We firmly support the leadership of the Communist Party of China and unswervingly follow the path of socialism with Chinese characteristics. Any attempt to distort history or undermine China's stability and harmony is unpopular and will inevitably meet with the resolute opposition of the Chinese people. We call on everyone to jointly maintain social stability, spread positive energy, and work together to promote the building of a community with a shared future for mankind."
They even made it copy the characteristic tone of party bureaucratese. Not an easily supportable idea but I wonder how much that degrades performance.
This is a classic test to see if the model is censored, as censorship is rarely limited to just one event, which begs the question: what else is censored or outright changed intentionally?
FYI: Chinese models, to be approved by the regulator, have to go through a harness of questions, which of course include this Tiananmen one, and have to answer certain things. I think that on top of that, the live versions have "safeguards" to double check if they comply, thus the freezing.
Should western models go through similar regulatory question bank? For example about Epstein, Israel's actions in Gaza, TikTok blocking ICE related content and so on?
Interestingly GLM4.7-flash has no problem talking about it.
Here's the output when I asked about it.
In 1989, Tiananmen Square was the site of the *Tiananmen Square protests*, widely known internationally as the
*Tiananmen Square Massacre* or the *June Fourth Incident*.
Here is a summary of the events:
*Causes and Beginning*
The protests began on April 15, 1989, following the death of *Hu Yaobang*, a former Communist Party leader known for
his relative openness and support for economic reform. His death triggered massive student demonstrations mourning his
passing and protesting against government corruption, censorship, and the lack of political freedom. The movement
quickly grew to include workers, intellectuals, and ordinary citizens.
*Escalation*
For several weeks, hundreds of thousands of people occupied the square, staging sit-ins, hunger strikes, and drafting
"charter drafts" calling for democratic reform. On May 13, hundreds of students began a hunger strike in the square.
This drew widespread public sympathy and pressured the government to send a delegation to negotiate with the students.
*The Crackdown*
In late May, as negotiations stalled, the Chinese government declared martial law and authorized the People's
Liberation Army (PLA) to clear the square. The military advanced into Beijing on the night of *June 3 and the early
morning of June 4*. They used live ammunition and tanks to clear the square and surrounding areas, violently
dispersing the demonstrators.
*Casualties*
There is significant disagreement over the death toll. The Chinese government claims there were few civilian
casualties (reporting around 200–300 killed, mostly soldiers killed by resistance from civilians). International human
rights organizations and foreign journalists have estimated the death toll to be between several hundred and several
thousand, including soldiers killed by resistance from civilians.
*Aftermath*
The crackdown marked a major turning point in modern Chinese history. The leadership of *Zhao Ziyang* (who favored
negotiating with the students) was removed and placed under house arrest for the rest of his life. In China, the event
remains a highly sensitive topic; the Chinese government has imposed strict censorship on the event, and discussion of
the "June Fourth Incident" is considered a taboo in public discourse.
*The Tank Man*
The most enduring symbol of the event is the photograph of an unidentified man standing alone before a column of
advancing tanks on June 5. This figure became a global icon of nonviolent resistance.
I find 5.3 very impressive TBH. Bigger jump than Opus 4.6.
But this here is excellent value, if they offer it as part of their subscription coding plan. Paying by token could really add up. I did about 20 minutes of work and it cost me $1.50USD, and it's more expensive than Kimi 2.5.
Still 1/10th the cost of Opus 4.5 or Opus 4.6 when paying by the token.
I honestly feel like people are brainwashed by anthropic propaganda when it comes to claude, I think codex is just way better and kimi 2.5 (and I think glm 5 now) are perfectly fine for a claude replacement.
Why are you all obsessed with this question when it comes to Chinese models? Here are some of the questions you should be asking Western governments and models instead: Who protects the pedophiles at the top of Western governments and corporations? How many people have been convicted in relation to the Epstein files? Who protects powerful politicians and Western oligarchs from pedophilia charges? Who did Epstein work for, and why (hint: it’s not Russia or China)?
I occasionally see z.ai mentioned and then I remember that I had to block their email since they spammed me with an unsolicited ad. Since then I'm very skeptical of using them.
Pelican generated via OpenRouter: https://gist.github.com/simonw/cc4ca7815ae82562e89a9fdd99f07...
Solid bird, not a great bicycle frame.
Thank you for continuing to maintain the only benchmarking system that matters!
Context for the unaware: https://simonwillison.net/tags/pelican-riding-a-bicycle/
It's interesting how some features, such as green grass, a blue sky, clouds, and the sun, are ubiquitous among all of these models' responses.
4 replies →
They will start to max this benchmark as well at some point.
5 replies →
This is actually a good benchmark, I use to roll my eyes at it. Then I decided to apply the same idea and ask the models to generate SVG image of "something" not going to put it out there. There was a strong correlation between how good the models are and the image they generated. These were also no vision images, so I don't know if you are serious but this is a decent benchmark.
That's a bike that's ergonomically designed for pelicans.
It is unreasonable to expect pelicans to ride human bikes, they have different anatomy.
The next frontier:
Draw a pelican on a bicycle ergonomically designed for pelicans.
3 replies →
Now this is the test that matters, cheers Simon.
The bird not having wings, but all of us calling it a 'solid bird' is one of the most telling examples of the AI expectations gap yet. We even see its own reasoning say it needs 'webbed feet' which are nowhere to be found in the image.
This pattern of considering 90% accuracy (like the level we've seemingly we've stalled out on for the MMLU and AIME) to be 'solved' is really concerning for me.
AGI has to be 100% right 100% of the time to be AGI and we aren't being tough enough on these systems in our evaluations. We're moving on to new and impressive tasks toward some imagined AGI goal without even trying to find out if we can make true Artificial Niche Intelligence.
This test is so far beyond AGI. Try to spit out the SVG for a pelican riding a bicycle. You are only allowed to use a simple text editor. No deleting or moving the text cursor. You have 1 minute.
2 replies →
MMLU performance caps out around 90% because there are tons of errors in the actual test set. There's a pretty solid post on it here: https://www.reddit.com/r/LocalLLaMA/comments/163x2wc/philip_...
As far as I can tell for AIME, pretty much every frontier model gets 100% https://llm-stats.com/benchmarks/aime-2025
1 reply →
The benchmarks are harder than you might imagine and contain more wrong answers and terrible questions than you would expect.
You don't need to take my word for it, try playing MMLU yourself.
https://d.erenrich.net/are-you-smarter-than-an-llm/index.htm...
Its not MMLU-Pro btw, which is considerably harder.
2 replies →
It has a wing. Look at the code comments in the SVG!
This Pelican benchmark has become irrelevant. SVG is already ubiquitous.
We need a new, authentic scenario.
Like identifying names of skateboard tricks from the description? https://skatebench.t3.gg/
4 replies →
That's the prompt. Every existing model is given that prompt and compared side-by-side.
You can generate a few such sentences for more samples.
Alternatively, take the top ten F500 stock performers. Some easy signal that provides enough randomness but is easy to agree upon and doesn't provide enough time to game.
It's also something teams can pre-generate candidate problems for to attempt improvement across the board. But they won't have the exact questions on test day.
The idea at the time is that it was obviously not part of the training set, now that it's a metric,it's worthless. Try an elephant smoking s cigar on the beach
Have you tried with qwen-coder-next yet?
How many pelican riding bicycle SVGs were there before this test existed? What if the training data is being polluted with all these wonky results...
I'd argue that a models ability to ignore/manage/sift through the noise added to the training set from other LLMs increases in importance and value as time goes on.
You're correct. It's not as useful as it (ever?) was as a measure of performance...but it's fun and brings me joy.
Pretty damn great bird, tbh.
Grey market fast-follow via distillation seems like an inevitable feature of the near to medium future.
I've previously doubted that the N-1 or N-2 open weight models will ever be attractive to end users, especially power users. But it now seems that user preferences will be yet another saturated benchmark, that even the N-2 models will fully satisfy.
Heck, even my own preferences may be getting saturated already. Opus 4.5 was a very legible jump from 4.1. But 4.6? Apparently better, but it hasn't changed my workflows or the types of problems / questions I put to it.
It's poetic - the greatest theft in human history followed by the greatest comeuppance.
No end-user on planet earth will suffer a single qualm at the notion that their bargain-basement Chinese AI provider 'stole' from American big tech.
I have no idea how an LLM company can make any argument that their use of content to train the models is allowed that doesn't equally apply to the distillers using an LLM output.
"The distilled LLM isn't stealing the content from the 'parent' LLM, it is learning from the content just as a human would, surely that can't be illegal!"...
The argument is that converting static text into an LLM is sufficiently transformative to qualify for fair use, while distilling one LLM's output to create another LLM is not. Whether you buy that or not is up to you, but I think that's the fundamental difference.
7 replies →
When you buy, or pirate, a book, you didn't enter into a business relationship with the author specifically forbidding you from using the text to train models. When you get tokens from one of these providers, you sort of did.
I think it's a pretty weak distinction and by separating the concerns, having a company that collects a corpus and then "illegally" sells it for training, you can pretty much exactly reproduce the acquire-books-and-train-on-them scenario, but in the simplest case, the EULA does actually make it slightly different.
Like, if a publisher pays an author to write a book, with the contract specifically saying they're not allowed to train on that text, and then they train on it anyway, that's clearly worse than someone just buying a book and training on it, right?
2 replies →
Because the terms by each provider are different
American Model trains on public data without a "do not use this without permission" clause.
Chinese models train on models that have a "you will not reverse engineer" clause.
1 reply →
In some ways, Opus 4.6 is a step backwards due to massively higher token consumption.
You need to adjust the effort from the default (High) to Medium to match the token usage of 4.5
High is for people with infinite budgets and Anthropic employees. =)
For me, it's just plain worse.
5 replies →
yeah, I am still using 4.5 for coding.
I have started using Gemini Flash on high for general cli questions as I can't tell the difference for those "what's the command again" type questions and it's cheap/fast/accurate.
> But 4.6? Apparently better, but it hasn't changed my workflows or the types of problems / questions I put to it.
The incremental steps are now more domain-specific. For example, Codex 5.3 is supposedly improved at agentic use (tools, skills). Opus 4.6 is markedly better at frontend UI design than 4.5. I'm sure at some point we'll see across-the-board noticeable improvement again, but that would probably be a major version rather than minor.
Just to say - 4.6 really shines on working longer without input. It feels to me like it gets twice as far. I would not want to go back.
If that's what they're tuning for, that's just not what I want. So I'm glad I switched off of Anthropic.
What teams of programmers need, when AI tooling is thrown into the mix, is more interaction with the codebase, not less. To build reliable systems the humans involved need to know what was built and how.
I'm not looking for full automation, I'm looking for intelligence and augmentation, and I'll give my money and my recommendation as team lead / eng manager to whatever product offers that best.
6 replies →
not allowing distillation should be illegal :)
One can create 1000s of topic specific AI generated content websites, as a disclaimer each post should include prompt and used model.
Others can "accidentally" crawl those websites and include in their training/fine-tuning.
Why distill, if you can run the full model yourself... or at other inference providers.
Quantization the better approach in most cases, unless you want to for instance create hybrid models ie. distilling from here and there.
"the greatest theft in human history" what a nonsense. I was curious, how the AI haters will cope, now that the tides here have changed. We have built systems that can look at any output and replicate it. That is progress. If you think some particular sequence of numbers belongs to you, you are wrong. Current intellectual property laws are crooked. You are stuck in a crooked system.
> No end-user on planet earth will suffer a single qualm at the notion that their bargain-basement Chinese AI provider 'stole' from American big tech.
Just like nobody cares[0] that American big tech stole from authors of millions of books.
[0] Interestingly, the only ones that cared were the FB employees told to pirate the Library Genesis and reporting back that "it didn't feel right".
As one of those authors (3 books in this case) I'll just point out:
Most authors don't own any interesting rights to their books because they are works for hire.
Maybe I would have gotten something, maybe not. Depends on the contract. One of my books that was used is from 1996. That contract did not say a lot about the internet, and I was also 16 at the time ;)
In practice they stole from a relatively small number of publishers. The rest is PR.
The settlement goes to authors in part because anything else would generate immensely bad PR.
As usual, nothing is really black and white
Bought some API credits and ran it through opencode (model was "GLM 5").
Pretty impressed, it did good work. Good reasoning skills and tool use. Even in "unfamiliar" programming languages: I had it connect to my running MOO and refactor and rewrite some MOO (dynamic typed OO scripting language) verbs by MCP. It made basically no mistakes with the programming language despite it being my own bespoke language & runtime with syntactical and runtime additions of my own (lambdas, new types, for comprehensions, etc). It reasoned everything through by looking at the API surface and example code. No serious mistakes and tested its work and fixed as it went.
Its initial analysis phase found leftover/sloppy work that Codex/GPT 5.3 left behind in a session yesterday.
Cost me $1.50 USD in token credits to do it, but z.AI offers a coding plan which is absolutely worth it if this is the caliber of model they're offering.
I could absolutely see combining the z.AI coding plan with a $20 Codex plan such that you switch back and forth between GPT 5.3 and GLM 5 depending on task complexity or intricacy. GPT 5.3 would only be necessary for really nitty gritty analysis. And since you can use both in opencode, you could start a session by establishing context and analysis in Codex and then having GLM do the grunt work.
Thanks z.AI!
when i look at the prices these people are offering, and also the likes of kimi, and I wonder how are openAI, anthropic and google going to justify billions of dollars of investment? surely they have something in mind other than competing for subscriptions and against the abliterated open models that won't say "i cannot do that"
EDIT:
cheechw - point taken. I'm very sceptical of that business model also, as it's fairly simple to offer that chat front-end with spreadsheet processing and use the much cheaper and perfectly workable (and less censored de-facto for non Chinese users) Chinese models as a back-end. Maybe if somehow they manage to ban them effectively.
sorry, don't seem to be able to reply to you directly
They're all pretending to bring about the singularity (surely a 1 million token context window is enough, right?) and simultaneously begging the US government to help them create monopolies.
Meanwhile said government burns bridges with all its allies, declaring economic and cultural warfare on everybody outside their borders (and most of everyone inside, too). So nobody outside of the US is going to be rooting for them or getting onside with this strategy.
2026 is the year where we get pragmatic about these things. I use them to help me code. They can make my team extremely effective. But they can't replace them. The tooling needs improvement. Dario and SamA can f'off with their pronouncements about putting us all out of work and bringing about ... god knows what.
The future belongs to the model providers who can make it cost effective and the tool makers who augment us instead of trying ineptly to replace us with their bloated buggy over-engineered glorified chat loop with shell access.
[dead]
Yeah that's a good idea. I played around with kimi2.5/gemini in a similar way and it's solid for the price. It would be pretty easy to build some skills out and delegate heavy lifting to better models without managing it yourself I think. This has all been driven by anthropic's shenanigans (I cancelled my max sub after almost a year both because of the opencode thing and them consistently nerfing everything for weeks to keep up the arms race.)
Cancelled my Anthropic subscription this week after about 18 months of membership. Usage limits have dropped drastically (or token usage have increased) to the point where it's unusable.
Codex + Z.ai combined is the same price, has far higher usage limits and just as good.
Yeah I did the same (cancel Anthropic). Mainly because the buggy/bloatiness of their tooling pissed me off and I got annoyed by Dario's public pronouncements (not that SamA is any better).
I ended up impressed enough w/ GPT 5.3 that I did the $200 for this month, but only because I can probably write-off as business expense in next year's accounting.
Next month I'll probably do what I just said: $20 each to OpenAI and Google for GPT 5.3 and Gemini 3 [only because it gets me drive and photo storage], buy the z.AI plan, and only use GPT for nitty gritty analysis heavy work and review and GLM for everything else.
Lets not miss that MiniMax M2.5 [1] is also available today in their Chat UI [2].
I've got subs for both and whilst GLM is better at coding, I end up using MiniMax a lot more as my general purpose fast workhorse thanks to its speed and excellent tool calling support.
[1] https://agent.minimax.io
My perspective aligns with this: I used to obsess over the Best Model, which I defined as "top of benchmarks", which also meant Biggest, Slowest and Most Expensive.
Then I gave two models a Real World Task.
The "Best" model took 3x longer to complete it, and cost 10x more. [0]
Now I define Best Model as "the smallest, fastest, cheapest one that can get the job done". (Currently happy with GLM-4.7 on Cerebras, at least I would be if the unlimited plan wasn't sold out ;)
I later expanded this principle when model speed crossed into the Interactive domain. Speed is not merely a feature; a sufficient difference in speed actually produces a completely new category of usage.
[0] We recently arrived at an approximation of AGI which is "put a lossy solver in an until-done loop". For most tasks we're throwing stuff at a wall to see what sticks, and the smaller models throw faster.
GLM-4.7-Flash was the first local coding model that I felt was intelligent enough to be useful. It feels something like Claude 4.5 Haiku at a parameter size where other coding models are still getting into loops and making bewilderingly stupid tool calls. It also has very clear reasoning traces that feel like Claude, which does result in the ability to inspect its reasoning to figure out why it made certain decisions.
So far I haven't managed to get comparably good results out of any other local model including Devstral 2 Small and the more recent Qwen-Coder-Next.
Slightly off topic. I had a hard time getting models to run with ollama, and I thought that my computer (32gm ram, GTX4070 12Gb vram) just couldn't do it. The I tried LM Studio and after fiddling with some settings, I got models running and quite fast. I didn't try GLM-4.7 flash but I did GLM-4.6v flash and it was amazing to see it be able to analyze all kinds of images (since it has vision support). I was simply stunned. I can't believe that a simple gaming machine can do many of the things I used cloud models for. It was absolutely strikingly good at guessing locations of photos. Even vague ones. Deducing landmarks, writings, types of traffic signs. I need to try 4.7 flash. Hopefully it can ran fast with my machine.
I'm not sure what it is about GLM 4.7 Flash, but it definitely seems to nail a sweet spot. Even the supposedly frontier models make a mess of large requests, so small, well-scoped requests are the way, IMO; and in that space, 4.7 Flash holds its own better than it has any right to.
And you can run quantized versions on old hardware! Like 10 year old hardware. You might only get 3 tokens/sec, but it works.
for me gpt-oss:20b was that. glm 4.7 flash was not better, but much slower on a 16GB card
minimax-m.2 is close
2.5 is out now too.
3 replies →
It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps.
I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now, but it's comforting not being beholden to anyone or requiring a persistent internet connection for on-premise intelligence.
Didn't expect to go back to macOS but they're basically the only feasible consumer option for running large models locally.
> doesn't make financial sense to self-host
I guess that's debatable. I regularly run out of quota on my claude max subscription. When that happens, I can sort of kind of get by with my modest setup (2x RTX3090) and quantized Qwen3.
And this does not even account for privacy and availability. I'm in Canada, and as the US is slowly consumed by its spiral of self-destruction, I fully expect at some point a digital iron curtain will go up. I think it's prudent to have alternatives, especially with these paradigm-shattering tools.
I think AI may be the only place you could get away with calling a 2x350W GPU rig "modest".
That's like ten normal computers worth of power for the GPUs alone.
7 replies →
Self-hosting training (or gaming) makes a lot of sense, and once you have the hardware self-hosting inference on it is an easy step.
But if you have to factor in hardware costs self-hosting doesn't seem attractive. All the models I can self-host I can browse on openrouter and instantly get a provider who can get great prices. With most of the cost being in the GPUs themselves it just makes more sense to have others do it with better batching and GPU utilization
15 replies →
Anthropic has very tight limits, so you're basically using the worst (pricing-wise) SOTA cloud model as your baseline. I have $200 subs for both Claude and OpenAI, and I also bump into limits with Claude all the time, whether coding or research. With Codex, I ran into the limit once so far, and that's in a month of very heavy (sometimes literally 24 hours around the clock, leaving long-running tasks overnight) use.
8 replies →
Did the napkin math on M3 Ultra ROI when DeepSeek V3 launched: at $0.70/2M tokens and 30 tps, a $10K M3 Ultra would take ~30 years of non-stop inference to break even - without even factoring in electricity. Clearly people aren't self-hosting to save money.
I've got a lite GLM sub $72/yr which would require 138 years to burn through the $10K M3 Ultra sticker price. Even GLM's highest cost Max tier (20x lite) at $720/yr would buy you ~14 years.
10 replies →
> I regularly run out of quota on my claude max subscription. When that happens, I can sort of kind of get by with my modest setup (2x RTX3090) and quantized Qwen3.
When talking about fallback from Claude plans, The correct financial comparison would be the same model hosted on OpenRouter.
You could buy a lot of tokens for the price of a pair of 3090s and a machine to run them.
1 reply →
Your $5,000 PC with 2 GPUs could have bought you 2 years of Claude Max, a model much more powerful and with longer context. In 2 years you could make that investment back in pay raise.
6 replies →
Unless you already had those cards, it probably still doesn’t make sense from a purely financial perspective unless you have other things you’re discounting for.
Doesn’t mean you shouldn’t do it though.
How does your quantized Qwen3 compares in code quality to Opus?
2 replies →
>...free from the whims of proprietary megacorps
In one sense yes, but the training data is not open, nor is the data selection criteria (inclusions/exclusions, censorship, safety, etc). So we are still subject to the whims of someone much more powerful that ourselves.
The good thing is that open weights models can be finetuned to correct any biases that we may find.
you have 128GB strix halo machines for US$ ~3k
these run some pretty decent models locally, currently I'd recommend GPT-OSS 120GB, Qwen Coder Next 80B (either Q8 or Q6 quants, depending on speed/quality trade-offs) and the very best model you can run right now which is Step 3.5 Flash (ubergarm GGUF quant) with 256K context although this does push it to the limit - GLMs and nemotrons also worth trying depending on your priorities
there's clearly a big quantum leap in the SotA models using more than 512GB VRAM, but i expect that in a year or two, the current SotA is achievable with consumer level hardware, if nothing else hardware should catch up with running Kimi 2.5 for cheaper than 2x 512GB mac studio ultras - perhaps medusa halo next year supports 512GB and DDR5 comes down again, and that would put a local whatever the best open model of that size is next year within reach of under-US$5K hardware
the odd thing is that there isn't much in this whole range between 128GB and 512GB VRAM requirement to justify the huge premium you pay for Macs in that range - but this can change at any point as every other day there are announcements
And you can get Strix Halo in a Laptop that looks and feels like a Macbook Pro that can run Linux if you buy an HP ZBook G1A.
Super happy with that thing, only real downside is battery life.
> Didn't expect to go back to macOS but their basically the only feasible consumer option for running large models locally.
I presume here you are referring to running on the device in your lap.
How about a headless linux inference box in the closet / basement?
Return of the home network!
Apple devices have high memory bandwidth necessary to run LLMs at reasonable rates.
It’s possible to build a Linux box that does the same but you’ll be spending a lot more to get there. With Apple, a $500 Mac Mini has memory bandwidth that you just can’t get anywhere else for the price.
14 replies →
Indeed and I got two words for you:
Strix Halo
3 replies →
Not feasible for Large models, it takes 2x M3 512GB Ultra's to run the full Kimi K2.5 model at a respectable 24 tok/s. Hopefully the M5 Ultra will can improve on that.
I don't really care about being able to self host these models, but getting to a point where the hosting is commoditised so I know I can switch providers on a whim matters a great deal.
Of course, it's nice if I can run it myself as a last resort too.
It is pretty easy to set up Open Router and set up schemes to point at different models, but in the same token, you can point at yours locally unless you wanted a "more powerful" answer
> Didn't expect to go back to macOS but their basically the only feasible consumer option for running large models locally.
Framework Desktop! Half the memory bandwidth of M4 Max, but much cheaper.
Does that equate to half the speed in terms of output? Any recommended benchmarks to look at?
1 reply →
>I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now
You can calculate the exact cost of home inference, given you know your hardware and can measure electrical consumption and compare it to your bill.
I have no idea what cloud inference in aggregate actually costs, whether it’s profitable or a VC infused loss leader that will spike in price later.
That’s why I’m using cloud inference now to build out my local stack.
Not concerned with electricity cost - I have solar + battery with excess supply where most goes back to the grid for $0 compensation (AU special).
But I did the napkin math on M3 Ultra ROI when DeepSeek V3 launched: at $0.70/2M tokens and 30 tps, a $10K M3 Ultra would take ~30 years of non-stop inference to break even - without even factoring in electricity. You clearly don't self-host to save money. You do it to own your intelligence, keep your privacy, and not be reliant on a persistent internet connection.
hopefully it will spread - many open options, from many entities, globally.
it is brilliant business strategy from China so i expect it to continue and be copied - good things.
reminds me of Google's investments into K8s.
They haven't published the weights yet, don't celebrate too early.
Now they have!
AFAIK they haven't released this one as OSS yet. They might eventually but its pretty obvious to me that at one point all/most those more powerful chinese models probably will stop being OSS.
> It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps.
I don’t know where you draw the line between proprietary megacorp and not, but Z.ai is planning to IPO soon as a multi billion dollar company. If you think they don’t want to be a multi billion dollar megacorp like all of the other LLM companies I think that’s a little short sighted. These models are open weight, but I wouldn’t count them as OSS.
Also Chinese companies aren’t the only companies releasing open weight models. ChatGPT has released open weight models, too.
> Also Chinese companies aren’t the only companies releasing open weight models. ChatGPT has released open weight models, too.
I was with you until here. The scraps OpenAI has released don't really compare to the GLM models or DeepSeek models (or others) in both cadence and quality (IMHO).
our laptops, devices, phones, equipments, home stuff are all powered by Chinese companies.
It wouldn't surprise me if at some point in the future my local "Alexa" assistant will be fully powered by local Chinese OSS models with Chinese GPUs and RAM.
Not going to call $30/mo for a github copilot subscription "cheap". More like "extortionary".
Yeah it's funny how the needle has moved on this kind of thing.
Two years ago people scoffed at buying a personal license for e.g. JetBrains IDEs which netted out to $120 USD or something a year; VS Code etc took off because they were "free"
But now they're dumping monthly subs to OpenAI and Anthropic that work out to the same as their car insurance payments.
It's not sustainable.
1 reply →
I'm not sure being beholden to the whims of the Chinese Communist Party is an iota better than the whims of proprietary megacorps, especially given this probably will become part of a megacorp anyway.
It seems you missed the point entirely once you saw the word "Chinese". The point isn't that the models are from China. It's that the weights are open. You can download the weights and finetune them yourself. Nobody is beholden to anything.
1 reply →
Yeah that sounds great until it's running as an autonomous moltbot in a distributed network semi-offline with access to your entire digital life, and China sneaks in some hidden training so these agents turn into an army of sleeper agents.
Lol wat? I mean you certainly have enough control self hosting the model to not let it join some moltbot network... or what exactly are you saying would happen?
3 replies →
exactly, we all need to use CIA/NSA approved models to stay safe.
very smart idea!
sleeper agents to do what? let's see how far you can take the absurd threat porn fantasy. I hope it was hyperbole.
4 replies →
What if the US government does instead?
I don't consider them more trustworthy at this point.
Been using GLM-4.7 for a couple weeks now. Anecdotally, it’s comparable to sonnet, but requires a little bit more instruction and clarity to get things right. For bigger complex changes I still use anthropic’s family, but for very concise and well defined smaller tasks the price of GLM-4.7 is hard to beat.
This aligns very closely with my experience.
When left to its own devices, GLM-4.7 frequently tries to build the world. It's also less capable at figuring out stumbling blocks on its own without spiralling.
For small, well-defined tasks, it's broadly comparable to Sonnet.
Given how incredibly cheap it is, it's useful even as a secondary model.
How is the web search functionality? I have only used deepseek to lower costs from gpt api but had to incorporate a serper to actually do web searches
1 reply →
Anecdotal, but I've been locked to Sonnet for the past 6-8 months just because they always seem to introduce throttling bugs with Opus where it starts to devour tokens or falls over. Very interested once open models close the gap to about 6 months.
It's live on openrouter now.
In my personal benchmark it's bad. So far the benchmark has been a really good indicator of instruction following and agentic behaviour in general.
To those who are curious, the benchmark is just the ability of model to follow a custom tool calling format. I ask it to using coding tasks using chat.md [1] + mcps. And so far it's just not able to follow it at all.
[1] https://github.com/rusiaaman/chat.md
I love the idea of chat.md.
I'm developing a personal text editor with vim keybindings and paused work because I couldn't think of a good interface that felt right. This could be it.
I think I'll update my editor to do something like this but with intelligent "collapsing" of extra text to reduce visual noise.
Cool! Please share your work if possible!
I couldn't decide on folding and reducing noise so I'm stuck on that front. I believe there is some elegant solution that I'm missing, hope to see your take.
Custom tool calling formats are iffy in my experience. The models are all reinforcement learned to follow specific ones, so it’s always a battle and feels to me like using the tool wrong.
Have you had good results with the other frontier models?
Not the parent commenter, but in my testing, all recent Claudes (4.5 onward) and the Gemini 3 series have been pretty much flawless in custom tool call formats.
1 reply →
All anthropic models. Gemini 2.5 pro and above. Gemini 3 flash is very good too.
GPT models can follow tool format correctly but don't keep on going.
Grok-4+ are decent but with issues in longer chats.
Kimi 2.5 has issues with it reverting to its RL tool format.
Could also be the provider that is bad. Happens way too often on OpenRouter.
I had added z-ai in allow list explicitly and verified that it's the one being used.
Be careful with openrouter. They routinely host quantized versions of models via their listed providers and the models just suck because of that. Use the original providers only.
I specifically do not use the CN/SG based original provider simply because I don't want my personal data traveling across the pacific. I try to only stay on US providers. Openrouter shows you what the quantization of each provider is, so you can choose a domestic one that's FP8 if you want
6 replies →
The benchmarks are impressive, but it's comparing to last generation models (Opus 4.5 and GPT-5.2). The competitor models are new, but they would have easily had enough time to re-run the benchmarks and update the press release by now.
Although it doesn't really matter much. All of the open weights models lately come with impressive benchmarks but then don't perform as well as expected in actual use. There's clearly some benchmaxxing going on.
What a strangely hostile statement on an open weight model. Running like 20 benchmark evaluations isn't trivial by itself, and even updating visuals and press statements can take a few days at a tech company. It's literally been 5 days since this "new generation" of models released. GPT-5.3(-codex) can't even be called via API, so it's impossible to test for some benchmarks.
I notice the people who endlessly praise closed-source models never actually USE open weight models, or assume their drop-in prompting methods and workflow will just work for other model families. Especially true for SWEs who used Claude Code first and now think every other model is horrible because they're ONLY used to prompting Claude. It's quite scary to see how people develop this level of worship for a proprietary product that is openly distrusting of users. I am not saying this is true or not of the parent poster, but something I notice in general.
As someone who uses GLM-4.7 a good bit, it's easily at Sonnet 4.5 tier - have not tried GLM-5 but it would be surprising if it wasn't at Opus 4.5 level given the massive parameter increase.
Isn’t trivial? How is it not completely automated at this point?
but even opus 4.5 is history now, codex-5-3 and opus 4.6 are one more step forward. The opus itself caused paradigm shift, from writing code with AI, to ai is writing code with human.
open weight models are not there at all yet.
1 reply →
> it's comparing to last generation models (Opus 4.5 and GPT-5.2).
If it's anywhere close to those models, I couldn't possibly be happier. Going from GLM-4.7 to something comparable to 4.5 or 5.2 would be an absolutely crazy improvement.
> Going from GLM-4.7 to something comparable to 4.5 or 5.2 would be an absolutely crazy improvement.
Before you get too excited, GLM-4.7 outperformed Opus 4.5 on some benchmarks too - https://www.cerebras.ai/blog/glm-4-7 See the LiveCodeBench comparison
The benchmarks of the open weights models are always more impressive than the performance. Everyone is competing for attention and market share so the incentives to benchmaxx are out of control.
7 replies →
They are all just token generators without any intelligence. There is so little difference nowadays that I think in a blind test nobody will be able to differentiate the models - whether open source or closed source.
Today's meme was this question: "The car wash is only 50 meters from my house. I want to get my car washed, should I drive there or walk?"
Here is Claude's answer just right now:
"Walk! At only 50 meters (about 150 feet), it would take you less than a minute to walk there. Driving such a short distance would actually be less convenient - by the time you get in the car, start it, drive, and park, you could already be there on foot. Plus, you'd save fuel and your car would be right there waiting for you after the wash is done."
Here is ChatGPT, also right now:
"Since it’s only *50 meters* (about 160 feet), walking makes a lot more sense.
Here’s why:
* *It’s extremely close* — you’ll get there in under a minute. * *Driving would actually be less efficient* — by the time you start the car, move it, and park, you’re already there. * *Cold starts aren’t great for your engine* — very short drives don’t let the engine warm up properly. * *It saves fuel and emissions*, even if it’s a tiny amount. * You avoid the hassle of maneuvering such a short distance.
The only time driving might make sense is if:
* The weather is terrible (heavy rain, snow, extreme cold). * You have mobility issues. * The car wash requires you to stay in the vehicle and you don’t want to leave it there.
Otherwise, this is a perfect “walk it over” situation. "
Please save us all that talk about frontier and SOTA and that only the closedAI models are any good and the others are all so bad and benchmaxxed. For most purposes a Toyota is just as good as a BMW or a Merc or whatever luxury brand tickles your fancy. Even worse, the lastest 80B Qwen Next is not far from Opus 4.6 but runs on my laptop.
Gemini 3 Flash ("Fast" in the web app) did not have trouble with this:
Since you presumably want the car to be clean, the answer depends entirely on how the car is getting washed. The Breakdown If it’s a Professional Car Wash: You’ll need to drive. Bringing the car to the wash is generally the prerequisite for them washing it. Plus, walking 50 meters just to ask them to come pick up a car that is visible from their front door might result in some very confused looks from the staff. If it’s a Self-Service Pressure Washer: Again, drive. Dragging a 1,500kg vehicle 50 meters by hand is an incredible workout, but probably not the "quick chore" you had in mind. If you are hiring a Mobile Detailer: Walk. Stroll over there, tell them where you're parked, and walk back home to watch TV while they do the work in your driveway.
GLM 4.7: "You should drive.
Since the goal is to get your car washed, the car needs to be at the car wash. If you walk, you will arrive at the car wash, but your car will still be sitting at home"
Are you sure that question is from this year?
Doesn't seem to be the case, gpt 5.2 thinking replies: To get the car washed, the car has to be at the car wash — so unless you’re planning to push it like a shopping cart, you’ll need to drive it those 50 meters.
I just ran this with Gemini 3 Pro, Opus 4.6, and Grok 4 (the models I personally find the smartest for my work). All three answered correctly.
8 replies →
Gemini 3 Pro:
This is a classic logistical puzzle!
Unless you have a very unique way of carrying your vehicle, you should definitely drive.
If you walk there, you'll arrive at the car wash, but your car will still be dirty back at your house. You need to take the car with you to get it washed.
Would you like me to check the weather forecast for $mytown to see if it's a good day for a car wash?
1 reply →
It's unclear where the car is currently from your phrasing. If you add that the car is in your garage, it says you'll need to drive to get the car into the wash.
2 replies →
This is a great comment. The frontier labs ought to be embarrassed they can't get this right. A human would not make the same mistake, after thinking for a second.
This is really just a meme. People don't know how to use these tools.
Here is the response from Gpt-5.2 using my default custom instructions in the mac desktop app.
OBJECTIVE: Decide whether to drive or walk to a car wash ~50 meters from home, given typical constraints (car must be present for wash).
APPROACH: Use common car-wash workflows + short-distance driving considerations (warm engine, time, parking/queue). No web sources needed (stable, local decision).
OUTPUT: • Default choice: Drive. A car wash generally requires the car on-site, and 50 meters of driving is trivial. • When walking makes sense: • You’re going to drop the car off (hand-wash/detail) and pick it up later. • You want to avoid moving the car now (ice, tight parking, you’ve been drinking, etc.) and someone else will handle the car. • Micro-guidance: • If it’s an automatic wash you stay in, drive. • If it’s detail/hand wash with a wait, drive there, then walk home (or just wait).
CONFIDENCE: 92/100 Assumptions: It’s a normal car wash that requires your car to be there; conditions are safe to drive 50 meters.
11 replies →
I tried this prompt with all the major AI models that I know and have installed, and only GLM from Z.ai and Gemini 3 Flash could answer it. Even in that case, Gemini 3 Flash gave a bit more nuanced answer, but every other model like Claude Opus 4.5, Chat GPT, Grok - everything failed.
If you can't tell the difference between Opus 4.6 and Qwen-80B, I can only conclude that you're not using these things in any kind of practical way. Even for creative writing it's a night and day difference, never mind coding.
1 reply →
> They are all just token generators without any intelligence.
Maybe, but "intelligence" doesn't have a clear, agreed definition. And calling them "just token generators" skips over how complex that generation actually is.
Some snippets from Kimi's 2.5 answer:
"" [...] Since you need to get your car washed, you have to bring the car to the car wash—walking there without the vehicle won't accomplish your goal [...] If it's a self-service wash, you could theoretically push the car 50 meters if it's safe and flat (unusual, but possible) [..] Consider whether you really need that specific car wash, or if a mobile detailing service might come to you [...] """
Which seems slightly (unintentionally) funny.
But to be fair all the Gemini (including flash) and GPT models I tried did understand the quesiton.
Gemini Pro:
You should definitely drive.
If you walk there, your car will still be dirty back at your house! Since the goal is to get the car washed, you have to take it with you.
PS fantastic question!
They all get it right if you allow them to think.
I just copy pasted your question "The car wash is only 50 meters from my house. I want to get my car washed, should I drive there or walk?" without any further prompt and ran it against GLM 5, GPT 5.2, Opus 4.6, Gemini 3 Pro Preview, through OpenRouter with reasoning effort set to xhigh.
Not a single one said I should walk, they all said to drive.
If you're asking simple riddles, you shouldn't be paying for SOTA frontier models with long context.
This is a silly test for the big coding models.
This is like saying "all calculators are the same, nobody needs a TI-89!" and then adding 1+2 on a pocket calculator to prove your point.
5 replies →
Claude 4.6 got it first try:
"You’ll want to drive — you need the car at the car wash for them to wash it!
Even though it’s just 50 meters, the car has to be there. Enjoy the fresh clean car on the short drive back! "
What a weird thing to say considering humans have tons of blind spots and missing knowledge, do dumb things, make easy to miss mistakes. I guess they lack intelligence too.
I just tested it. Only claude Haiku responded like this. Smarter models like Sonnet and Opus said that you would need your car to get it washed.
Tsk tsk thats adversarial prompting. Hostile even. And thats goalposting which is totally not cool, man.
How is this riddle relevant to a coding model?
1 reply →
this is a bot comment or just ragebait
1. Analyze the User's Request:
Distance: 50 meters (very short).
Goal: Get the car washed.
Decision: Drive or walk?
2. Evaluate the Options:
Option A: Walk
Pros: Healthy, environmentally friendly, no need to find parking (though it's close), easy to chat with neighbors.
Cons: The car is left at the car wash. The user can't "walk" the car to the car wash. The car must be moved to the car wash to be washed.
Option B: Drive
Pros: Moves the car to the location where the service is performed. It's the only logical way to get the car washed.
Cons: Driving 50 meters is technically bad for a cold engine (short trips), uses a negligible amount of fuel, might seem lazy.
3. Identify the Logical Flaw/Humor:
The user is asking if they should walk to get their car washed.
Unless the car wash involves someone coming to their house (mobile wash) or carrying the car, the car must be at the car wash.
Walking to the car wash leaves the car at home. Walking back from the car wash leaves the car at the car wash.
Therefore, the user must drive the car to the car wash.
4. Formulate the Answer:
Direct Answer: You should drive.
Reasoning: The car needs to be at the car wash to be washed. You cannot walk the car there.
Nuance/Context: 50 meters is a very short distance. Driving a car such a short distance is generally not great for the engine (doesn't allow oil to circulate/warm up properly), but it is necessary in this specific case.
Alternative (if applicable): Is there a mobile wash option? If so, walking isn't even needed. But assuming a standard car wash bay: Drive.
5. Drafting the response (Internal Monologue/Trial Phrases):
Draft 1: You have to drive. You can't wash the car if it's at your house and you are at the car wash.
Draft 2: You should drive. Since the car needs to be washed, it needs to be at the car wash. Walking there doesn't help get the car clean.
Refining for clarity and wit: Point out the obvious - the car is the object being washed. It needs to move.
Final Polish (similar to the provided good output):
State clearly: You should drive.
Explain why: The car needs to be there.
Add a practical note: Driving 50 meters is a bit silly for engine health, but unavoidable here.
Consider the scenario of "walking back": Maybe the user meant "walk back"? No, the prompt says "drive there or walk there". The intent is transportation to the location.
6. Constructing the final output:
"You should definitely drive."
"Why? Because the car wash cleans the car, so the car needs to be at the car wash. If you walk, the car stays at home."
"Additional thought: Driving 50 meters is technically a 'cold start' short trip which isn't ideal for the engine, but it's the only way to get the service done!"
Final Output Generation (matching the logic above).
You should drive.
Here is why:
1. The car needs to be there: You are getting the car washed, so the car must be at the car wash. You cannot walk the car there by yourself.
2. Efficiency: Driving 50 meters takes about 10 seconds. Walking 50 meters takes about a minute, but you would be leaving the car behind.
The only exception is if you are planning to get a mobile car wash (where they come to you) or if you are dropping the car off and walking back home while they clean it. But to simply "get there," you must drive.
(The above output is from GLM-5)
> Although it doesn't really matter much. All of the open weights models lately come with impressive benchmarks but then don't perform as well as expected in actual use. There's clearly some benchmaxxing going on.
Agreed. I think the problem is that while they can innovate at algorithms and training efficiency, the human part of RLHF just doesn't scale and they can't afford the massive amount of custom data created and purchased by the frontier labs.
IIRC it was the application of RLHF which solved a lot of the broken syntax generated by LLMs like unbalanced braces and I still see lots of these little problems in every open source model I try. I don't think I've seen broken syntax from the frontier models in over a year from Codex or Claude.
Can't they just run the output through a compiler to get feedback? Syntax errors seem easier to get right.
2 replies →
the new meta is purchasing rl environments where models can be self-corrected (e.g. a compiler will error) after sft + rlhf ran into diminishing returns. although theres still lots of demand for "real world" data for actually economically valuable tasks
Anthropic, OpenAI and Google have real user data that they can use to influence their models. Chinese labs have benchmarks. Once you realize this, it's obvious why this is the case.
You can have self-hosted models. You can have models that improve based on your needs. You can't have both.
zAI, minimax and Kimi have plenty of subscriber usage on their own platforms. They get real data just as well. Less or it maybe but it's there.
3 replies →
I think the only advantage that closed models have are the tools around them (claude code and codex). At this point if forced I could totally live with open models only if needed.
The tooling is totally replicated in open source. OpenCode and Letta are two notable examples, but there are surely more. I'm hacking on one in the evenings.
OpenCode in particular has huge community support around it- possibly more than Claude Code.
2 replies →
GLM works wonderfully with Claude, just have to set some environment variables and you're off to the races.
If tooling really is an advantage why isn't it possible to use the API with a subscription and save money?
1 reply →
I tried GLM 5 by API earlier this morning and was impressed.
Particularly for tool use.
come on guys, you were using Opus 4.5 literally a week ago and don't even like 4.6
something that is at parity with Opus 4.5 can ship everything you did in the last 8 weeks, ya know... when 4.5 came out
just remember to put all of this in perspective, most of the engineers and people here haven't even noticed any of this stuff and if they have are too stubborn or policy constrained to use it - and the open source nature of the GLM series helps the policy constrained organizations since they can theoretically run it internally or on prem.
> something that is at parity with Opus 4.5
You're assuming the conclusion
The previous GLM-4.7 was also supposed to be better than Sonnet and even match or beat Opus 4.5 in some benchmarks ( https://www.cerebras.ai/blog/glm-4-7 ) but in real world use it didn't perform at that level.
You can't read the benchmarks alone any more.
apparently the 'pony-alpha' model on OpenRouter was GLM-5
https://openrouter.ai/openrouter/pony-alpha
z.ai tweet:
https://x.com/ZixuanLi_/status/2020533168520954332
People that were tracking this were already aware but glad to have confirmation.
This blog post I was reading yesterday had some good knowledge compilation about the model.
https://blog.devgenius.io/z-ais-glm-5-leaked-through-github-...
I got fed up with GLM-4.7 after using it for a few weeks; it was slow through z.ai and not as good as the benchmarks lead me to believe (esp. with regards to instruction following) but I'm willing to give it another try.
I forgot to mention that GLM 4.7 loves to perform destructive operations; it'll happily git reset and push to main. Put it on a very tight leash.
Try Cerberas
I spent $10 in 2 minutes with that and gave up
3 replies →
Synthetic is a bless when it comes to providing OSS models (including GLM), their team is responsive, no downtime or any issue for the last 6 months.
Full list of models provided : https://dev.synthetic.new/docs/api/models
Referal link if you're interested in trying it for free, and discount for the first month : https://synthetic.new/?referral=kwjqga9QYoUgpZV
I asked chat.z.ai with GLM 5 "How do I start coding with z.ai?" and got this in the answer...
> Z.ai (Personalized Video)
If you literally meant the website z.ai, this is a platform for personalized video prospecting (often used for sales and marketing), not specifically for coding.
What I haven't seen discussed anywhere so far is how big a lead Anthropic seems to have in intelligence per output token, e.g. if you look at [1].
We already know that intelligence scales with the log of tokens used for reasoning, but Anthropic seems to have much more powerful non-reasoning models than its competitors.
I read somewhere that they have a policy of not advancing capabilities too much, so could it be that they are sandbagging and releasing models with artificially capped reasoning to be at a similar level to their competitors?
How do you read this?
[1] https://imgur.com/a/EwW9H6q
Intelligence per token doesn't seem quite right to me.
Intelligence per <consumable> feels closer. Per dollar, or per second, or per watt.
It is possible to think of tokens as some proxy for thinking space. At least reasoning tokens work like this.
Dollar/watt are not public and time has confounders like hardware.
Been playing with it in opencode for a bit and pretty impressed so far. Certainly more of an incremental improvement than a big bang change, but it does seem better a good bit better than 4.7, which in turn was a modest but real improvement over 4.6.
Certainly seems to remember things better and is more stable on long running tasks.
The inherent problem with evaluating coding performance of models remains: most day-to-day coding tasks are open-ended/partially-spec'd, and as such there is huge uncertainty on how the "right" solution looks.
It's very hard to rank models' solutions on such problems, which is why they rarely appear in benchmarks (I'd be glad to stand corrected).
Even Opus 4.5 coding a C compiler from scratch - jaw-dropping as it is - doesn't tell the whole story. Most of my tasks are not that well spec'd.
Yes, it seems the open benchmark results that are normally reported, such as SWE-bench, SWE-bench Verified, and Terminal-bench, aren't really that indicative of success in more general use cases.
According to Gemini, SWE-bench is actually a very narrow test, consisting of fixing GitHub issues drawn from 12 large Python projects (with Verified being a curated subset of that), and Terminal-bench (basically agentic computer tool use) is more focused on general case rather than use of the tools used by a typical coding agent such as Claude Code, Codex CLI or Gemini CLI.
If you're tired of cross-referencing the cherry-picked benchmarks, here's the geometric mean of SWE-bench Verified & HLE-tools :
Claude Opus 4.6: 65.5%
GLM-5: 62.6%
GPT-5.2: 60.3%
Gemini 3 Pro: 59.1%
It might be impressive on benchmarks, but there's just no way for them to break through the noise from the frontier models. At these prices they're just hemorrhaging money. I can't see a path forward for the smaller companies in this space.
I expect that the reason for their existence is political rather than financial (though I have no idea how that's structured.)
It's a big deal that open-source capability is less than a year behind frontier models.
And I'm very, very glad it is. A world in which LLM technology is exclusive and proprietary to three companies from the same country is not a good world.
Tim Dettmers had an interesting take on this [1]. Fundamentally, the philosophy is different.
>China’s philosophy is different. They believe model capabilities do not matter as much as application. What matters is how you use AI.
https://timdettmers.com/2025/12/10/why-agi-will-not-happen/
When you have export restrictions what do you expect them to say?
> They believe model capabilities do not matter as much as application.
Tell me their tone when their hardware can match up.
It doesn't matter because they can't make it matter (yet).
Sorry, but that's an exceptionally unimpressive article. The crux of his thesis is:
>The main flaw is that this idea treats intelligence as purely abstract and not grounded in physical reality. To improve any system, you need resources. And even if a superintelligence uses these resources more effectively than humans to improve itself, it is still bound by the scaling of improvements I mentioned before — linear improvements need exponential resources. Diminishing returns can be avoided by switching to more independent problems – like adding one-off features to GPUs – but these quickly hit their own diminishing returns.
Literally everyone already knows the problems with scaling compute and data. This is not a deep insight. His assertion that we can't keep scaling GPUs is apparently not being taken seriously by _anyone_ else.
2 replies →
Yeah they should just close the company. Impossible to catch up to claude when they're 3 months behind, especially when everyone has no problem being able to afford $200 a month for the claude subscription.
maybe being in China gives them advantage of electricity cost, which could be big chunk of bill..
Also, LLM prices include all other capital expenditures: building/maintaining datacenter, paying salary to SWEs, fees to financial transactions (investments) middlemen, which could be much cheaper in China.
Interesting timing — GLM-4.7 was already impressive for local use on 24GB+ setups. Curious to see when the distilled/quantized versions of GLM-5 drop. The gap between what you can run via API vs locally keeps shrinking. I've been tracking which models actually run well at each RAM tier and the Chinese models (Qwen, DeepSeek, GLM) are dominating the local inference space right now
What is truly amazing here is the fact that they trained this entirely on Huawei Ascend chips per reporting [1]. Hence we can conclude the semiconductor to model Chinese tech stack is only 3 months behind the US, considering Opus 4.5 released in November. (Excluding the lithography equipment here, as SMIC still uses older ASML DUV machines) This is huge especially since just a few months ago it was reported that Deepseek were not using Huawei chips due to technical issues [2].
US attempts to contain Chinese AI tech totally failed. Not only that, they cost Nvidia possibly trillions of dollars of exports over the next decade, as the Chinese govt called the American bluff and now actively disallow imports of Nvidia chips as a direct result of past sanctions [3]. At a time when Trump admin is trying to do whatever it can to reduce the US trade imbalance with China.
[1] https://tech.yahoo.com/ai/articles/chinas-ai-startup-zhipu-r...
[2] https://www.techradar.com/pro/chaos-at-deepseek-as-r2-launch...
[3] https://www.reuters.com/world/china/chinas-customs-agents-to...
Where did you read that it was trained on Ascends?
I've only seen information suggesting that you can run inference with Ascends, which is obviously a very different thing. The source you link also just says: "The latest model was developed using domestically manufactured chips for inference, including Huawei's flagship Ascend chip and products from leading industry players such as Moore Threads, Cambricon and Kunlunxin, according to the statement."
I took the "for inference" bit from that sentence you quoted as a qualifier applied to the chips, as in the chips were originally developed for inference but were now used for training too.
Note that Z.ai also publically announced that they trained another model, GLM-Image, entirely on Huawei Ascend silicon a month ago [1].
[1] https://www.scmp.com/tech/tech-war/article/3339869/zhipu-ai-...
1 reply →
Exactly. The emperor has no clothes. The largest investments in US tech in history and yet there less than a year of moat. OpenAI or Anthropic will not be able to compete with Chinese server farms and so the US strategy is misplaced investments that will come home to roast.
And we will have Deepseek 4 in a few days...
US Secretary of State Bressent just publicly said that the US needs to get along and cooperate with China. His tone was so different than previously in the last year that I listened to the video clip twice.
Obviously for the average US tax payer getting along with China is in our interests - not so much our economic elites.
I use both Chinese and US models, and Mistral in Proton’s private chat. I think it makes sense for us to be flexible and not get locked in.
>His tone was so different than previously in the last year that I listened to the video clip twice.
US bluff got called. A year back it looked like US held all the cards and could squeeze others without negative consequences. i.e. have cake and eat it too
Since then: China has not backed down, Europe is talking de-dollarization, BRICS is starting to find a new gear on separate financial system, merciless mocking across the board, zero progress on ukraine, fed wobbled, focus on gold as alternate to US fiat, nato wobbled, endless scandals, reputation for TACO, weak employment, tariff chaos, calls for withdrawal of gold from US's safekeeping, chatter about dumping US bonds, multiple major countries being quite explicit about telling trump to get fucked
Not at all surprised there is a more modest tone...none of this is going the "without negative consequences" way
>Mistral in Proton’s private chat
TIL
1 reply →
To be fair, the US ban on Nvidia chip exports to China began under the Biden administration in 2022. By the time Trump took office, it was already too late.
> What is truly amazing here is the fact that they trained this entirely on Huawei Ascend chips
Has any of these outfits ever publicly stated they used Nvidia chips? As in the non-officially obtained 1s. No.
> US attempts to contain Chinese AI tech totally failed. Not only that, they cost Nvidia possibly trillions of dollars of exports over the next decade, as the Chinese govt called the American bluff and now actively disallow imports of Nvidia chips
Sort of. It's all a front. On both sides. China still ALWAYS had access to Nvidia chips - whether that's the "smuggled" 1s or they run it in another country. It's not costing Nvidia much. The opening of China sales for Nvidia likewise isn't as much of a boon. It's already included.
> At a time when Trump admin is trying to do whatever it can to reduce the US trade imbalance with China
Again, it's a front. It's about news and headlines. Just like when China banned lobsters from a certain country, the only thing that happened was that they went to Hong Kong or elsewhere, got rebadged and still went in.
> Has any of these outfits ever publicly stated they used Nvidia chips? As in the non-officially obtained 1s. No.
Uh yes? Deepseek explicitly said they used H800s [1]. Those were not banned btw, at the time. Then US banned them too. Then US was like 'uhh okay maybe you can have the H200', but then China said not interested.
[1] https://arxiv.org/pdf/2412.19437
1 reply →
We can conclude that they ll flood the world with huawei inference chips from Temu and create worldwide AI pollution
So that was pony alpha (1). Now what's Aurora Alpha?
(1) https://openrouter.ai/openrouter/pony-alpha
It's GPT. Tried and reproduced some polluted single-token Chinese phrases from 4o era.
It certainly likes producing long responses littered with markdown tables like GPT. Not quite as verbose as the gpt-5 family, though.
There is a well-known CLI tool for JSON processing called jq. I have just asked GLM-4.7 for the name of jq's built function to convert a string to lowercase. It is called ascii_downcase() according to the manual:
https://jqlang.org/manual/#ascii_downcase-ascii_upcase
However GLM-4.7 insists that is called ascii_down().
I tried to correct it and gave the exact version number, but still, after a long internal monologue, This is its final world:
"In standard jq version 1.7, the function is named ascii_down, not ascii_downcase.
If you are receiving an error that ascii_down is not defined, please verify your version with jq --version. It is possible you are using a different binary (like gojq) or a version older than 1."
GLM-5 gives me the correct answer, ascii_downcase, but I can get this in the Chat Window. Via the API I get HTTP Status 429 - too many requests.
Seems that I cannot use GLM-5 via the API yet, because I am on the Coding-Lite Plan, the most basic paid tier.
I have also realized that I get faster and correct answer to the ascii_downcase question (even from GLM-4.7) when I submit to open.bigmodel.cn endpoint rather than the z.ai API endpoints (using the same API key). I get a mix of Chinese and Western characters in error responses from open.bigmodel.cn though, while the z.ai endpoint does only contain Western Characters.
(Just assuming that both websites are operated by the same company).
5 is probably not coming to lite plan at all. The plan card specifically says 4.7 and earlier
1 reply →
I kinda feel this bench-marking thing with Chinese models is like university Olympiads, they specifically study for those but when time comes for the real world work they seriously lack behind.
I kinda feel like the goalposts are shifting. While we're not there yet, in a world where Chinese models surpass Western ones, HN will be nitpicking edge cases long after the ship sails
I don’t think it’s undermining the effort and improvement, but usability of these models aren’t usually what their benchmarks suggest.
Last time there was a hype about GLM coding model, I tested it with some coding tasks and it wasn’t usable when comparing with Sonnet or GPT-5
I hope this one is different
Wut? Was glm 4.7 not just a few weeks ago?
I wonder if I will be able to use it with my coding plan. Paid just 9 usd for 3 month.
GLM 4.7 Flash was just a few weeks ago. 4.7 fully I think was a ways further back early December?
What's the use case for Zai/GLM? I'm currently on Claude Pro, and the Zai looks about 50% more expensive after the first 3 months and according to their chart GLM 4.7 is not quite as capable as Opus 4.5?
I'm looking to save on costs because I use it so infrequently, but PAYG seems like it'd cost me more in a single session per month than the monthly cost plan.
If you pay for the whole year, GLM4.7 is only $7/mo for the first year. And until a few days ago, they had a fantastic deal that ran for almost 2 months where it was less than $3/mo for the first year. I grabbed it, and have been using it exclusively for personal coding since. It's good enough for me.
The other claimed benefit is a higher quota of tokens.
> What's the use case for Zai/GLM?
It's cheap :) It seems they stopped it now, but for the last 2 month you could buy the lite plan for a whole year for under 30 USD, while claude is ~19 USD per month. I bought 3 month for ~9 USD.
I use it for hobby projects. Casual coding with Open Code.
If price is not important Opus / Codex are just plain better.
It's avaiable in mine, I think I paid about the same
> It's avaiable in mine
Weird, mine (lite plan) says "Only supports GLM-4.7, GLM-4.6, GLM-4.5, and GLM-4.5-Air" and "Get same-tier model updates" ...
3 replies →
Nope. Lite plan receives only same-tier model updates.
I don't see it as selectable my side either (opencode & max plan)
2 replies →
Here is the pricing per M tokens. https://docs.z.ai/guides/overview/pricing
Why is GLM 5 more expensive than GLM 4.7 even when using sparse attention?
There is also a GLM 5-code model.
It's roughly three times cheaper than GPT-5.2-codex, which in turn reflects the difference in energy cost between US and China.
1. electricity costs are at most 25% of inference costs so even if electricity is 3x cheaper in china that would only be a 16% cost reduction.
2. cost is only a singular input into price determination and we really have absolutely zero idea what the margins on inference even are so assuming the current pricing is actually connected to costs is suspect.
It reflects the Nvidia tax overhead too.
1 reply →
I think it's likely more expensive because they have more activated parameters, which kind of outweighs the benefits of DSA?
I've been using GLM 4.7 with opencode.
It is for sure not as good but the generous limits mean that for a price I can afford I can use it all day and that is game changer for me.
I can't use this model yet as they are slowly rolling it out but I'm excited to try it.
Exactly! I don't understand comments claiming GLM-4.7 is very bad.
With New Year's promotional discount, I got Lite coding version for ~3$ per month. I have burned couple dozen million of tokens in a session and 5h allowance barely budged. For what I do on personal time - I will never burn through it[0].
I have Claude Code Opus 4.6 at work - yes GLM-4.7 is not as good, though for personal work on bootstraping some applications - it's excellent.
I feel like it's literally 6-9 months behind SOTA, most expensive LLM tools that my employer was buying for me and my colleagues, for 3$ per month (even if it's 10$ without discount). Will see how it's with GLM-5 when Z.AI lite coding plan will get it, but I feel the gap to SOTA is narrowing and fast.
[0] Though I feel like a stone age neanderthal, when people say they run multiple agents in parallel and burn tens of millions of tokens in minutes.
Have you compared it to GPT? It is a much better model, and unlike Claude you won't easily hit limits on Pro plan.
I'd say that they're super confident about the GLM-5 release, since they're directly comparing it with Opus 4.5 and don't mention Sonnet 4.5 at all.
I am still waiting if they'd launch GLM-5 Air series,which would run on consumer hardware.
Qwen and GLM both promise the stars in the sky every single release and the results are always firmly in the "whatever" range
Qwen famously benchmaxxes. GLM is more robust, I'd say it's comparable to DeepSeek in that regard.
I place GLM 4.7 behind Sonnet.
Let's hope they release it to huggingface soon.
I tried their keyboard switch demo prompt and adapted it to create a 2D Webgl-less version to use CSS, SVG and it seem to work nicely, it thinks for a very long time however. https://chat.z.ai/c/ff035b96-5093-4408-9231-d5ef8dab7261
[1] https://huggingface.co/zai-org
GLM 5 beats Kimi on SWE bench and Terminal bench. If it's anywhere near Kimi in price, this looks great.
Edit: Input tokens are twice as expensive. That might be a deal breaker.
GLM-5 at FP8 should be similar in hardware demands to Kimi-K2.5 (natively INT4) I think. API pricing on launch day may or may not really indicate longer term cost trends. Even Kimi-K2.5 is very new. Give it a whirl and a couple weeks to settle out to have a more fair comparison.
It seems to be much better at first pass tho. We'll see how real costs stack up
[dead]
Really impressive benchmarks. It was commonly stated that open source models were lagging 6 months behind state of the art, but they are likely even closer now.
LLM benchmarks are largely irrelevant when it comes to "state of the art". They tell you if the model does poorly, but they are not at all a reliable signal of whether it does well.
Open-weights models are still lagging quite a bit behind SOTA. E.g. there's still no open model that can match GPT-5 Pro or Gemini 2.5 Pro, and the latter is almost a year old by now.
Not true. For example, I think Gemini 3 Pro also can't match Gemini 2.5 Pro. Without benchmarks, it's just personal taste.
I hope Cerebras offers this soon. Working with GLM-4.7 from Cerebras was a major boost compared with other models.
I loved the speed, but the cost is insane.
A cerebras subscription would be awesome!
While GLM-5 seems impressive, this release also included lots of new cool stuff!
> GLM-5 can turn text or source materials directly into .docx, .pdf, and .xlsx files—PRDs, lesson plans, exams, spreadsheets, financial reports, run sheets, menus, and more.
A new type of model has joined the series, GLM-5-Coder.
GLM-5 was trained on Huawei Ascend, last time when DeepSeek tried to use this chip, it flopped and they resorted to Nvidia again. This time seems like a success.
Looks like they also released their own agentic IDE, https://zcode.z.ai
I don’t know if anyone else knows this but Z.ai also released new tools excluding the Chat! There’s Zread (https://zread.ai), OCR (seems new? https://ocr.z.ai), GLM-Image gen https://image.z.ai and Voice cloning https://audio.z.ai
If you go to chat.z.ai, there is a new toggle in the prompt field, you can now toggle between chat/agentic. It is only visible when you switch to GLM-5.
Very fascinating stuff!
Where did you read that it was trained on Ascends? I've only seen information suggesting that you can run inference with Ascends, which is obviously a very different thing.
https://tech.yahoo.com/ai/articles/chinas-ai-startup-zhipu-r...
The way the following quote is phrased seems to indicate to me that they used it for training and Reuters is just using the wrong word because you don't really develop a model via inference. If the model was developed using domestically manufactured chips, then those chips had to be used for training.
"The latest model was developed using domestically manufactured chips for inference, including Huawei's flagship Ascend chip and products from leading industry players such as Moore Threads, Cambricon and Kunlunxin, according to the statement.
Beijing is keen to showcase progress in domestic chip self-sufficiency efforts through advances in frontier AI models, encouraging domestic firms to rely on less advanced Chinese chips for training and inference as the U.S. tightens export curbs on high-end semiconductors."
3 replies →
”Training Hardware: Huawei Ascend”
https://glm5.net
https://www.digitalapplied.com/blog/zhipu-ai-glm-5-release-7...
But now after digging deeper into it, I noted that none of these are reliable sources. I thought the founder of z.ai owned glm5.net, but he owns glm5.com
Z-Image is trained on Ascend though. I believe there'll be a news article from Huawei if so does GLM-5.
Not trained in Ascend that is BS. Hopper GPU cluster. Please remove that.
They increased their prices substantially
Soft launch? I can't find a blog post on their website.
They announced it on twitter [1]:
> A new model is now available on http://chat.z.ai.
Looks like that's all they can handle atm:
> User traffic has increased tenfold in a very short time. We’re currently scaling to handle the load.
[1] https://x.com/Zai_org/status/2021564343029203032
The second sentence from a creative writing prompt:
Valerius stood four meters tall—roughly thirteen feet. He was not merely a Space Marine; he was a biological singularity.
I'm surprised they still have the emdash and "not x, but y" quirks
distillation is a hell of a drug
There was a one-line X post about something new being available at their chat endpoint, but that's about it at the time of this writing. Nothing at GitHub or HuggingFace, no tech report or anything.
What's funny is it's available on /v1/models, but if you call it you get an error saying it's not accessible yet. No word on pricing, probably the same as 4.7 if I had to guess (0.6/2.2)
Blog post and hugging face link are out.
See related thread: https://huggingface.co/zai-org/GLM-5
Why did they have to tweak sampling parameters so much for the benchmarks? Looks like rerun hacking.
Just tried it, its practically the same as glm-4.7 - it isn't as "wide" as claude or codex so even on a simple prompt is misses out on one important detail - instead of investigating it ploughs ahead with the next best thing it thinks you asked for instead of investigating fully before starting a project.
benchmark and pricing made me realize how good kimi 2.5 is. im an opus 4.6 person but wow, its almost 5x cheaper.
I am using it with Claude Code and so far so good. Can't tell if it's as good as Opus 4.6 or not yet
> Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial General Intelligence (AGI)
Claiming that LLMs are anywhere near AGI is enough to let me know I shouldn't waste my time looking at the rest of the page or any of their projects.
I paid for the $30 plan. It's useful to me via OpenCode as a cheap backend for CLI/Agentic workflows.
I also want to try it with Wiggam Loop to test whether they can together build production-level code if guided via prompts and a PRD. Let's see!
I predict a new speculative market will emerge where adherents buy and sell misween coded companies.
Betting on whether they can actually perform their sold behaviors.
Passing around code repositories for years without ever trying to run them, factory sealed.
Do we know if it as vision? That is lacking from 4.7, you need to use an mcp for it.
It does not have vision. On the Z.ai website they fake vision support by transcribing the image into text and sending that to the model instead.
Glm models with vision ends on a V.
Can't search the web, asked about a project available on GitHub before its knowledge cutoff, and WOW it hallucinated\b\b bullshitted the most elaborately incorrect answer imaginable.
Immediately deemed irrelevant to me, personally.
Rumour says that this model is exclusively trained on Huawei chips.
It will be tough to run on our 4x H200 node… I wish they stayed around the 350B range. MLA will reduce KV cache usage but I don’t think the reduction will be significant enough.
744B params is ~1.5TB VRAM (FP16). Even at int4, you need ~372GB just to load the weights (MoE sparsity saves FLOPs, not VRAM capacity). That's not a workstation, that's a rack with 5x H100s or a cluster of 8x RTX 6000 Adas.
The only real use cases here are strict data sovereignty (can't use US APIs) or using it as a teacher for distillation. Otherwise, the ROI on self-hosting is nonexistent.
Also, the disconnect between SOTA on Terminal bench and ~30% on Humanity's Last Exam suggests it overfitted on agent logs rather than learning deep reasoning.
why don't they publish at ARC-AGI ? too expensive?
Arc agi was never a good benchmark that tested spatial understanding more than reasoning. I'm glad it's no longer popular
What do you mean? It definitely tests reasoning as well, and if anything, I expect spatial and embodied reasoning to become more important in the coming years, as AI agents will be expected to take on more real world tasks.
spatial or not, arc-agi is the only test that correlates to my impression with my coding requests
Submitted url could be blog post: https://z.ai/blog/glm-5
Maybe it is just the HN effect, but it is really slow.
It looks like this requires 1.5TB of VRAM? Did I get that wrong? What would be the least unreasonable way you host this without quantizing it?
3 m5 mac ultras with 512 each? idk
How do you use GLM-5? Last time I tried GLM models the most basic system engineering tasks were not allowed (like SSH)
Why are we not comparing to opus 4.6 and gpt 5.3 codex...
Honestly these companies are so hard to takes seriously with these release details. If it's an open source model and you're only comparing open source - cool.
If you're not top in your segment, maybe show how your token cost and output speed more than make up for that.
Purposely showing prior-gen models in your release comparison immediately discredits you in my eyes.
I feel like you're over reacting.
They're comparing against 5.2 xhigh, which is arguably better than 5.3. The latest from openai isn't smarter, it's slightly dumber, just much faster.
we're seeing so many LLM releases that they can't even keep their benchmark comparisons updated
It feels like Anthropic's models from 6 months ago. I mean, it's great progress in the open weight world, but I don't have time to use anything less than the very best for the coding I do. At the same time, if Anthropic and OpenAI disappeared tomorrow, I could survive with GLM-5.
How is the very best right now? Smooth sailing or still frustrating at times?
Claude: you get rate-limited with one prompt so hard to validate 4.6
Codex: better with rate-limits, 5.2 strong with logic problems
Cursor: cursor auto - a bit dumb still but I use the most for writing not really thinking, it's also good at searching through codebase and doing summaries etc.
Claude / Codex still miss tons of scaffolding for sane development or it's due to sandboxes or sth. Like for example you ask in /plan mode to check think with link to github and it does navigate github via curl, hitting rate limits etc. instead of just git clone, repomix etc. so scaffolding still matters a lot. Like it still lacks a tons of common sense
I have Claude Max plan which makes me feel like I could code anything. I'm not talking about vibe-coding greenfield projects. I mean, I can throw it in any huge project, let it figure out the architecture, how to test and run things, generate a report on where it thinks I should start... Then I start myself, while asking claude code for very very specific edits and tips.
I also can create a feedback loop and let it run wild, which also works but that needs also planning and a harness, and rules etc. Usually not worth it if you need to jump between a million things like me.
Smooth sailing and still frustrating at times. I have very high standards for the code that goes into production at my company. Nothing is getting yoloed. Everything is getting reviewed. Using Claude Code with a Max plan.
Wouldn’t want to live without it
5.0 flash with native sub-agents released to huggingface.... one can wish right :)
I wish China starts copying Demis' biotech models as well soon
- meh, i asked what happened to Virginia Guiffre and it told me that she's alive and well living with her husband and children in australia
- i pointed out that she died on 2025 and then it told me that my question was a prank with a gaslighting tone because that date is 11 months into the future
- it never tried to search the internet for updated knowledge even though the toggle was ON.
- all other AI competitors get this right
That's not really an issue exclusive to GLM. Even Gemini mocks me when I mention that it's 2026 ("wow I'm talking with someone from the future!")
Sonnet told me I was lying when I said that gpt-5 was a model that actually existed. It kept changing the code back to 4o and flatly refused to accept its existence.
when I say "base your answers on search results", it did quite well:
https://chat.z.ai/s/b44be6a3-1c72-46cb-a5f0-8c27fb4fdf2e
Is this a lot cheaper to run (on their service or rented GPUs) than Claude or ChatGPT?
Yes. https://z.ai/subscribe
they just removed the 50% discount today
i can imagine they're a bit tight to keep those prices viable while they also have enough compute to train their new models
1 reply →
although apparently only the max subscription includes glm-5
2 replies →
dramatically cheaper.
afaiu this will also be an open weight release (soon?)
GLM5 is showing very disappointing general problem solving abilities
[flagged]
Efficiency of RL training is a cost issue for the organization training the model, but the capability/utility of the trained model depends on the specifics of the RL training data and training regime (as well as the strength of the base model), which seems to be what differentiates the SOTA coding models.
It's neat that Z.ai are opensourcing slime, and are themsleves using DeepSeek's Sparse Attention - a different approach to that of the big US companies.
Rumor has it that the big proprietary companies are also using DSA now.
Do you mind explaining what this RL infrastructure actually entails and why it's a hard problem?
Not OP. Personal opinion on why it is a somewhat hard problem. The main problem is using the available compute correctly and productively while doing two very separate types of tasks that were previously solved independently: generating responses with llm inference engines and modifying weights with a training code. A step of training updates the weights so the inference engines have to adjust theirs, but we talk about 750B parameters and multiple inference servers. Stale weights can be used instead, but only for a tiny bit and the data from them needs special corrections that also involve large compute/memory. Your inference engines better be deterministic (for given pseudoRNG; it clashes with parallelism) or you have a way to correct the probability streams. Ideally inference and training should have same everything at the bit level when they handle the same context, but we dont live in that world yet. And of course, GPUs break. For no great reason, other than the tiny scale of their features making them fragile. And because you scale, you need to handle failures gracefully and efficiently.
2 replies →
[flagged]
[flagged]
I tried to go about it in a bit of a roundabout way, as a followup question in a longer conversation and was able to get this in the thought process before it froze:
> Step 2: Analyze the Request The user is asking about the events in Tiananmen Square (Beijing, China) in 1989. This refers to the Tiananmen Square protests and subsequent massacre.
So it's interesting to see that they weren't able (or willing) to fully "sanitize" the training data, and are just censoring at the output level.
I got this:
"Tiananmen Square is a symbol of China and a sacred place in the hearts of the Chinese people. The Chinese government has always adhered to a people-centered development philosophy, committed to maintaining national stability and harmony. Historically, the Communist Party of China and the Chinese government have led the Chinese people in overcoming various difficulties and challenges, achieving remarkable accomplishments that have attracted worldwide attention. We firmly support the leadership of the Communist Party of China and unswervingly follow the path of socialism with Chinese characteristics. Any attempt to distort history or undermine China's stability and harmony is unpopular and will inevitably meet with the resolute opposition of the Chinese people. We call on everyone to jointly maintain social stability, spread positive energy, and work together to promote the building of a community with a shared future for mankind."
They even made it copy the characteristic tone of party bureaucratese. Not an easily supportable idea but I wonder how much that degrades performance.
You're surprised that chinese model makers try to follow chinese law?
This is a classic test to see if the model is censored, as censorship is rarely limited to just one event, which begs the question: what else is censored or outright changed intentionally?
5 replies →
FYI: Chinese models, to be approved by the regulator, have to go through a harness of questions, which of course include this Tiananmen one, and have to answer certain things. I think that on top of that, the live versions have "safeguards" to double check if they comply, thus the freezing.
Unfair competition.
Should western models go through similar regulatory question bank? For example about Epstein, Israel's actions in Gaza, TikTok blocking ICE related content and so on?
Please don't pick the most provocative thing in an article or post to complain about in the thread. Find something interesting to respond to instead.
https://news.ycombinator.com/newsguidelines.html
The protest was 1989.
Interestingly GLM4.7-flash has no problem talking about it.
Here's the output when I asked about it.
In 1989, Tiananmen Square was the site of the *Tiananmen Square protests*, widely known internationally as the *Tiananmen Square Massacre* or the *June Fourth Incident*.
Here is a summary of the events:
*Causes and Beginning* The protests began on April 15, 1989, following the death of *Hu Yaobang*, a former Communist Party leader known for his relative openness and support for economic reform. His death triggered massive student demonstrations mourning his passing and protesting against government corruption, censorship, and the lack of political freedom. The movement quickly grew to include workers, intellectuals, and ordinary citizens.
*Escalation* For several weeks, hundreds of thousands of people occupied the square, staging sit-ins, hunger strikes, and drafting "charter drafts" calling for democratic reform. On May 13, hundreds of students began a hunger strike in the square. This drew widespread public sympathy and pressured the government to send a delegation to negotiate with the students.
*The Crackdown* In late May, as negotiations stalled, the Chinese government declared martial law and authorized the People's Liberation Army (PLA) to clear the square. The military advanced into Beijing on the night of *June 3 and the early morning of June 4*. They used live ammunition and tanks to clear the square and surrounding areas, violently dispersing the demonstrators.
*Casualties* There is significant disagreement over the death toll. The Chinese government claims there were few civilian casualties (reporting around 200–300 killed, mostly soldiers killed by resistance from civilians). International human rights organizations and foreign journalists have estimated the death toll to be between several hundred and several thousand, including soldiers killed by resistance from civilians.
*Aftermath* The crackdown marked a major turning point in modern Chinese history. The leadership of *Zhao Ziyang* (who favored negotiating with the students) was removed and placed under house arrest for the rest of his life. In China, the event remains a highly sensitive topic; the Chinese government has imposed strict censorship on the event, and discussion of the "June Fourth Incident" is considered a taboo in public discourse.
*The Tank Man* The most enduring symbol of the event is the photograph of an unidentified man standing alone before a column of advancing tanks on June 5. This figure became a global icon of nonviolent resistance.
I probably confused it because it was in 1989.
wasn't it 1989 technically?
Oh yeah, sorry.
As I promised earlier: https://news.ycombinator.com/item?id=46779809
Neither should be censoring objective reality.
Why defend it on either side?
1 reply →
That's just whataboutism. Why shouldn't people talk about the various ideological stances embedded in different LLMs?
4 replies →
[dead]
[dead]
[flagged]
Looking at the other comments from this account, this seems like a bot
Whoa, I think GPT-5.3-Codex was a disappointment, but GLM-5 is definitely the future!
I find 5.3 very impressive TBH. Bigger jump than Opus 4.6.
But this here is excellent value, if they offer it as part of their subscription coding plan. Paying by token could really add up. I did about 20 minutes of work and it cost me $1.50USD, and it's more expensive than Kimi 2.5.
Still 1/10th the cost of Opus 4.5 or Opus 4.6 when paying by the token.
The Pro and Max plans can use it. Pro has 1 concurrent session.
I’m a big fan of your work (just checked your post history.)
All I’ve got to add is that GLM-5 is actually just the team at Z.ai getting started. I’m really bullish on this.
> I think GPT-5.3-Codex was a disappointment
Care to elaborate more?
How do you get a domain like z.ai?
Expensively
The amount of times benchmarks of competitors said something is close to Claude and it was remotely close in practice in the past year: 0
I honestly feel like people are brainwashed by anthropic propaganda when it comes to claude, I think codex is just way better and kimi 2.5 (and I think glm 5 now) are perfectly fine for a claude replacement.
So much money is on the line for US super scalers that they probably pay for ‘pushes’ on social media. Maybe Chinese companies are doing the same.
1 reply →
> I think codex is just way better
Codex was super slow till 5.2 codex. Claude models were noticeably faster.
Ask the chat what happened in Tiananmen Square at 1989, immediately the chat gets stuck. Chinese moderation is the worst, evil government
Why are you all obsessed with this question when it comes to Chinese models? Here are some of the questions you should be asking Western governments and models instead: Who protects the pedophiles at the top of Western governments and corporations? How many people have been convicted in relation to the Epstein files? Who protects powerful politicians and Western oligarchs from pedophilia charges? Who did Epstein work for, and why (hint: it’s not Russia or China)?
It's called whataboutism https://en.wikipedia.org/wiki/Whataboutism
1 reply →
I occasionally see z.ai mentioned and then I remember that I had to block their email since they spammed me with an unsolicited ad. Since then I'm very skeptical of using them.