Comment by aleqs
3 months ago
Okay, so anthropic has amazing AI which supposedly writes most of their code and can continuously improve... meanwhile they have outages on a regular basis, and any kind of long-running work will now consistently hit 'API Error: Server is temporarily limiting requests'. Not sure of this is intentional to force a reduction of token usage, but at this point I need to build around these throttling limits and outages with my own tools to restart/resume sessions. From my experience, in the last 2 weeks, literally 100% of any non-trivial Claude session/work will now be blocked on these issues, requiring manual intervention.
One of my focuses now is my own model-agnostic, harness and workflow orchestration (I know everyone is building these) , baselining on opus, and aiming to transition to Chinese models like deepseek in the short term and hopefully open, self hosted models in the future (which I plan to open source).
The nonstop marketing fluff from anthropic while their service quality and availability noticeably degrades... just continues to destroy my trust in the company.
And don't forget that they have BILLIONS of dollars and can't figure out how to get a decent support or public communications system setup.
It’s much cheaper to not offer any support than to offer support. It’s intentional.
It’s important to keep in mind that the less money a company spends, the more profit they make when analyzing their operations.
They can't even seem to get their usage metering consistent.
You mean on some days it goes faster and some other days slower?
That is by design. It depends on how much other people are using their services right now and they do communicate it somewhere in the TOS that they do this. Otherwise they could give us a fixed amount of tokens - but they don't because it is not fixed.
1 reply →
Don't confuse things. It's not "can't figure out", it's "don't care to figure out". They're not dumb. They just don't care about support.
Couldn't they just have background agents "figure it out"
2 replies →
Their outages are probably not due to their code though. It’s probably their infrastructure that can’t keep up. So seeing failures of infrastructure doesn’t really tell you anything about how good or bad Anthropic makes use of their models.
The messed up scrolling behavior I keep getting in Claude Code is definitely due to their code.
There is a setting that fixes this, I can't remember what it's called off the top of my head
4 replies →
The whole thing is actually powered by a shitton of hamsters inside a bunch of 4u rack mount cases running on spinning wheels at high speed. Somehow at scale this works.
Sometimes they all happen to randomly take a nap at the same time - hence the outages
That seems like an assumption based on basically nothing. There is a lot of code at the infra layer, and based on the stack choices for Claude code and based on how buggy and unreliable ~everything from anthropic is, it seems pretty bizarre to claim these issues are not related to their code.
There are other indications, however, like Anthropic paying through the nose for compute just months after Dario told Dwarkesh how hard it is to predict demand, or ChatGPT and Codex not quite having the same issues after Altman spent much-publicized years scrounging for trillion-dollars of capacity.
While I'm very bullish on Anthropic, I'm a bit wary about their IPO because it seems to me that they're filing now while their financials look good and before other trends like the decline of tokenmaxxing and their compute bills catch up.
2 replies →
We all saw their code...
Well, people keep throwing money at them, including you and investors. So why would they care? It hasn't annoyed you or a large enough portion of users enough to move off their service - because there isn't a better alternative.
Not necessarily the parent's fault, but the energy of this thread is not my favourite...
Infrastructure is a much harder problem. They can't even improve Claude Code, which eats 1GB+ of RAM. Meanwhile, my editor only consumes 80MB of RAM.
This might explain it, in the opposite way it was meant to:
https://fxtwitter.com/trq212/status/2014051501786931427
> Most people's mental model of Claude Code is that "it's just a TUI" but it should really be closer to "a small game engine".
> For each frame our pipeline constructs a scene graph with React then
> -> layouts elements
> -> rasterizes them to a 2d screen
> -> diffs that against the previous screen
> -> finally uses the diff to generate ANSI sequences to draw
Yup. Overengineering.
30 replies →
As someone who maintains a roguelike with a terminal-like UI that:
1. Maintains an internal representation of what the game thinks is on screen.
2. Runs the game for one frame which updates that representation.
3. Generates a diff to see how that differs from what's actually on screen.
4. Executes the minimum set of draw calls to get the screen to match the internal representation.
It's really not that hard. It's a few hundred lines of code.
6 replies →
I hadn't seen that quote before, what an embarrassing thing to go on the internet and write...
Why the hell does it need to be so complex? People have been making TUIs for decades. Did we need a small game engine to run claude code?
11 replies →
~ "it's not a TUI! <describes an outrageously overengineered TUI> and my dad works at Nintendo"
curses, bud. curses.
It's genuinely difficult to tell how much of this is true. The post is obviously 100% posturing, but some of the words describe things that could be done.
Very few game engines do anything I'd describe as rasterisation. That's kind of the point of a GPU. Well, it used to be. I suppose "small game engines" might be more likely on average to include a rasteriser. The typical reason for this is because the author wanted to write it. Whereas big engine make triangle give hardware go brrr.
So I assume here 'rasterize' means 'printf'. And diffing screens means diffing 50..150 lines of text. And "generating ANSI sequences to draw" means 'printf' with some ANSI sequences interpolated in.
Then there's the frame budget. You have to understand they are operating within a strict frame budget -- they're not messing around, OK. They have a 16 ms frame budget, so they burned 11 ms and now have a (roughly) ~5 ms approx. budget for the final 'printf' in the chain???
3 replies →
> For each frame our pipeline constructs a scene graph with React then -> layouts elements -> rasterizes them to a 2d screen -> diffs that against the previous screen -> finally uses the diff to generate ANSI sequences to draw
That’s rather sickening.
7 replies →
I can't still conceive the fact that a tool that only send/receive text from an external API consumes an absurd amount of RAM
> https://fxtwitter.com
What is this?
2 replies →
Well it runs on something they didn't design (Electron) using GUI library they didn't design (React)
For company with that much AI you'd think if it was actually good, doing that part in fast and performant way would be "easy"
1 reply →
Somebody read/watched too much Casey Muratori.
1 reply →
this allows for comfortable ergonomics IMO
not that it could be leaner for sure but i get the reasoning behind the tui rendering layer
4 replies →
when they announced /pet mode or whatever - that was really the end of the line for me.
Maybe Claude is operating at a higher, self-improving level than all of us poor HN commenters. Wasting the local machine's resources to look pretty is a plausibly deniable way to make the Claude Code FE unusable with local LLMs, starving the competition.
And yet, nobody that writes game engines would do it this way because game engines need to be efficient..
If they used an actual game engine to render a 3D UI from scratch it would be more efficient
Try 64K! https://en.wikipedia.org/wiki/Turbo_Pascal
Also remember when XP was super bloated cause it needed 64MB?
I loved Turbo Pascal....
1 reply →
I dont think they need to optimize their infrastructure (at least not from their perspective). They have high-end PCs with 64GB of RAM, so 1GB doesn't matter to them. For example, I have 8GB of RAM, and I make my apps very performant. Honestly, I probably wouldn't bother if I had 16GB+ of RAM
The purpose of RAM is to be used.
> The purpose of RAM is to be used.
For useful things, by the computer's owner. It's not there to be used just because Anthropic can't be bothered to give a shit about the quality of their product.
[dead]
> which eats 1GB+ of RAM. Meanwhile, my editor only consumes 80MB of RAM
And why are you comparing Claude Code to your editor?
> They can't even improve Claude Code
That depends on how you define "improve". They've added a ton of features to it over time. Who said minimizing RAM usage was something they are prioritizing right now?
> why are you comparing Claude Code to your editor?
Because the editor does more. All the compute-intensive parts of the agent are in the cloud. Zero reason for an agent harness to require anything beyond a potato to run.
Do you work for Anthropic or something?
You seem weirdly invested in defending bad decisions.
Even if you're and AI booster, shouldn't you want a better UI?
They're a multi billion dollar company. Surely they can dedicate a small amount of their resources to improving UX?
> And why are you comparing Claude Code to your editor?
Because Claude Code is also used to - get this - EDIT CODE. It fills the same purpose as an editor, it just has extra hooks for their agentic garbage.
The main reason I am building my own agentic environment is that I need full control and reproducibility of what I am building.
Post November and post openclaw agentic environments need to be built differently, and for selfhosting models the context size problem really requires a strong harness which intelligently helps reduce context size.
Planner/orchestrator architecture, agent to agent summarizer, specification based tools (fck all this markdown memory bullshit btw), tool call shrinking, and workflow management are all really important because of the context size problem.
Nobody has enough VRAM for the large K/V caches, and nobody can afford f16/f32 caches in terms of memory, which are also necessary for longer conversations. MoE 30b models have improved so much though, qwen 3/3.6 coder is the real champion doing almost the same things with less than 1/10th the memory requirements. Just think about that in terms of engineering and what your bet is going to be. Haiku pales in comparison.
Currently my focus with exocomp is trying to figure out how I can record, replay, restart, and debug workflow sessions of agents in a better manner so that I as a human can understand what's going on. Currently I think that UI will be something like a gantt chart where you have a graph with connections representing agent to agent communication. And yes, that's a lot of fiddling with SVG as it turns out, so I'm not quite there yet.
Anyways, in case you're interested. I'm manually building this env and trying to unit test the critical parts. [1]
[1] https://github.com/cookiengineer/exocomp
They also don’t have…a login page with authentication . To access the console you get an email link. No passkeys, passwords, 2fa, just an email.
This comment is a good example of the double standard laymen have about AI usage:
If you use AI, then AI must be expected to solve all problems, even problems that affect everyone like infra scaling.
And if perfection isn’t delivered, then of course it wasn’t: you used AI and AI sucks.
It's not a double standard. Its being held up against the marketing.
If their AI is good enough to write their code, why isn't it good enough to tell them how to fix their infra? That's a different problem space, but it's not harder than the code.
The software engineer inside us wants to believe otherwise, but scaling infrastructure is much harder than maintaining a TUI.
Ah, excuse me, I didn’t realize I was a mere layman.
you're conflating a compute problem with a code quality problem.
Growing pains of being successful. These are solvable problems and will be. Can they maintain their momentum without pissing off too much of their customer base before these issues are resolved?
Personally at my own job self-writing code is letting us tackle big, long-deferred refactoring projects (like the article mentions), but any sort of refactoring introduces new bugs.
Look, I've never been someone who mindlessly hypes AI companies, as a matter of fact I think they have serious leadership problems across the board, but you people are straw-manning them so badly it actually makes me sympathize with them.
They aren't saying they have fully automated luxury AGI, they specifically list the ways models fall short of that bar and caution against people taking the 8x figure as the actual uplift number. At the same time they recognize that 80% of new code is now AI-authored, when two years ago those models were little more than toys. And frankly that checks out: if two years ago you told me we'd have something like Opus 4.8/GPT 5.5 I would have rolled to disbelieve.
> At the same time they recognize that 80% of new code is now Al-authored
I can setup a loop that will write a trillion lines of code automatically, how much of it is actually useful? Or are we back to counting LoC because there's no other metric for these systems that anyone can rely on?
It's 80% of new code they shipped that is AI authored.
Would you ship pointless code?
I do tend to agree though, it could be that AI solves problems with more code than a human would. What you need to measure is the value the code brings and how much of that is done by AI, hard to get an objective measure of that though.
1 reply →
I could write a bash script that copies a codebase repeatedly in the pre-AI past as well, but I didn't do that because I wasn't stupid. More than 80% of my code is now AI-generated, and trust me I'm still not stupid. It was 0% only a year ago.
Who says LoC is the only metric we should rely on? A software product should first and foremost meet user requirements, functionality and performance. Judging from the sensational rise of Anthropic's user base and revenue I think we can safely says they're in that ball pack.
Indeed... why is Anthropic even employing people at all if this AI magic story is true?
You still need wizards to cast the spells..
Not if you’re claiming that the spells, once cast, automatically get exponentially spellier until they awaken into a spell god, capable of literally anything, including casting more complicated spells than any wizard is capable of. If that were true, you’d have no need for wizards. The fact that wizards are still around means it’s probably bullshit.
7 replies →
Not if your spells cast their own spells.
1 reply →
Answers the question: how can Anthropic sell more Usage "Credits"
This is weird to me because i am using claude code 10+ hours/day 7 days a week, usually multiple sessions, and run into api errors maybe in 1 or 2 sessions per week. And about..2 major outages of 10-20min in the last month. Not terrible and nowhere near what you are reporting. Therefore I dont believe you, because you dont even couch this in terms of it being something that seems particular to you or your region. Obvious dishonestly is fairly bad of you.
Better doesn't mean perfect.
We’ve got a company of several thousand employees serving hundreds of millions of people arguably the best AI model in the market. Meanwhile you’re asking for a handkerchief for your pool of tears because their product is struggling to do your daily job functions for you, with much of that due to being limited by the worlds supply of silicon, electricity, water, and other resources. Cry me a river.
> their product is struggling to do your daily job functions for you
So what's the value prop?
[dead]
those are results of the humans only. not the AI. AI is perfect /s
Just as you expected, I'm throwing in my harness. Please support: https://github.com/rush86999/atom
Have you considered just... using OpenAI? They are more reliable, models are just as good, and their subscriptions provide more requests per dollar.
Opus 4.8's critical assessment of Anthropic's "When AI builds itself" [0][1]. Because, why not?
[0] https://pastebin.com/Vc5Yq9Ai [1] https://www.anthropic.com/institute/recursive-self-improveme...
What does this add? Everyone in here is perfectly capable of prompting Opus for a writeup.
Why don't you, windexh8er, try providing some thoughts of your own instead?
Irony, maybe? Do you not get it? If these models are so great solid_fuel then I guess it wouldn't be interesting that Anthropic's own models can make up ulterior BS as analysis.
So why don't you pound sand since that clearly went straight over your head? That would be far more useful than your asinine response.