Comment by bastard_op
1 day ago
I've been doing something a lot like this, using a claude-desktop instance attached to my personal mcp server to spawn claude-code worker nodes for things, and for a month or two now it's been working great using the main desktop chat as a project manager of sorts. I even started paying for MAX plan as I've been using it effectively to write software now (I am NOT a developer).
Lately it's gotten entirely flaky, where chat's will just stop working, simply ignoring new prompots, and otherwise go unresponsive. I wondered if maybe I'm pissing them off somehow like the author of this article did.
Now even worse is Claude seemingly has no real support channel. You get their AI bot, and that's about it. Eventually it will offer to put you through to a human, and then tell you that don't wait for them, they'll contact you via email. That email never comes after several attempts.
I'm assuming at this point any real support is all smoke and mirrors, meaning I'm paying for a service now that has become almost unusable, with absolutely NO means of support to fix it. I guess for all the cool tech, customer support is something they have not figured out.
I love Claude as it's an amazing tool, but when it starts to implode on itself that you actually require some out-of-box support, there is NONE to be had. Grok seems the only real alternative, and over my dead body would I use anything from "him".
Anthropic has been flying by the seat of their pants for a while now and it shows across the board. From the terminal flashing bug that’s been around for months to the lack of support to instabilities in Claude mobile and Code for the web (I get 10-20% message failure rates on the former and 5-10% on CC for web).
They’re growing too fast and it’s bursting the seams of the company. If there’s ever a correction in the AI industry, I think that will all quickly come back to bite them. It’s like Claude Code is vibe-operating the entire company.
The Pro plan quota seems to be getting worse. I can get maybe 20-30 minutes work done before I hit my 4 hour quota. I found myself using it more just for the planning phase to get a little bit more time out of it, but yesterday I managed to ask it ONE question in plan mode (from a fresh quota window), and while it was thinking it ran out of quota. I'm assuming it probably pulled in a ton of references from my project automatically and blew out the token count. I find I get good answers from it when it does work, but it's getting very annoying to use.
(on the flip side, Codex seems like it's being SO efficient with the tokens it can be hard to understand its answers sometimes, it rarely includes files without you doing it manually, and often takes quite a few attempts to get the right answer because it's so strict what it's doing each iteration. But I never run out of quota!)
Very happy to see that I am not the only one. My pro subscription lasts maybe 30 minutes for the 5 hour limit. It is completely unusable and that's why I actually switched to OpenCode + GLM 4.7 for my personal projects and. It's not as clever as Opus 4.5 but it often gets the job done anyway
Claude Code allegedly auto-includes the currently active file and often all visible tabs and sometimes neighboring files it thinks are 'related' - on every prompt.
The advice I got when scouring the internets was primarily to close everything except the file you’re editing and maybe one reference file (before asking Claude anything). For added effect add something like 'Only use the currently open file. Do not read or reference any other files' to the prompt.
I don't have any hard facts to back this up, but I'm sure going to try it myself tomorrow (when my weekly cap is lifted ...).
9 replies →
^ THIS
I've run out of quota on my Pro plan so many times in the past 2-3 weeks. This seems to be a recent occurrence. And I'm not even that active. Just one project, execute in Plan > Develop > Test mode, just one terminal. That's it. I keep getting a quota reset every few hours.
What's happening @Anthropic ?? Anybody here who can answer??
46 replies →
I never run out of this mysterious quota thing. I close Claude Code at 10% context and restart.
I work for hours and it never says anything. No clue why you’re hitting this.
$230 pro max.
6 replies →
Self-hosted might be the way to go soon. I'm getting 2x Olares One boxes, each with an RTX 5090 GPU (NVIDIA 24GB VRAM), and a built-in ecosystem of AI apps, many of which should be useful, and Kubernetes + Docker will let me deploy whatever else I want. Presumably I will manage to host a good coding model and use Claude Code as the framework (or some other). There will be many good options out there soon.
3 replies →
I've used the Anthropic models mostly through Openrouter using aider. With so much buzz around Claude Code I wantes to try it out and thought that a subscription might be more cost efficient for me. I was kinda disappointed by how quickly I hit the quota limit. Claude Code gives me a lot more freedom than what aider can do, on the other side I have the feeling that pure coding tasks work better through aider or Roo Code. The API version is also much much faster that the subscription one.
3 replies →
We’re an Anthropic enterprise customer, and somehow there’s a human developer of theirs on a call with us just about every week. Chatting, tips and tricks etc.
I think they are just focusing on where the dough is.
[dead]
You are giving me images from The Bug Short where the guy goes to investigate mortgages and knocks on some random person’s door to ask about a house/mortgage just to learn that it belongs to a dog. Imagine finding out that Anthropic employs no humans at all. Just an AI that has fired everyone and been working on its own releases and press releases since.
"Just an AI that has fired everyone"
At least it did not turn against them physically... "get comfortable while I warm up the neurotoxin emitters"
'The Big Short' (2015)
They whistleblowed themselves that Claude Cowork was coded by Claude Code… :)
You can tell they’re all vibe coded.
Claude iOS app, Claude on the web (including Claude Code on the web) and Claude Code are some of the buggiest tools I have ever had to use on a daily basis. I’m including monstrosities like Altium and Solidworks and Vivado in the mix - software that actually does real shit constrained by the laws of physics rather than slinging basic JSON and strings around over HTTP.
It’s an utter embarrassment to the field of software engineering that they can’t even beat a single nine of reliability in their consumer facing products and if it wasn’t for the advantage Opus has over other models, they’d be dead in the water.
8 replies →
Whistleblowed dog food.
1 reply →
I think your surmise is probably wrong. It's not that their growing to fast, it's that their service is cheaper than the actual cost of doing business.
Growth isn't a problem unless you dont actually pay for the cost of every user you subscribe. Uber, but for poorly profitable business models.
Well, they vibe code almost every tool at least
Claude Code has accumulated so much technical dept (+emojis) that Claude Code can no longer code itself.
6 replies →
> I'm paying for a service now that has become almost unusable, with absolutely NO means of support to fix it.
Isn’t the future of support a series of automations and LLMs? I mean, have you considered that the AI bot is their tech support, and that it’s about to be everyone else’s approach too?
Support has been automated for a while, LLMs just made it even less useful (and it wasn't very useful to begin with; for over a decade it's been a Byzantine labyrinth of dead-ends, punji-pits and endless hours spent listening to smooth jazz).
Yup, the main goal of customer support for almost every Internet-based company for over a decade now is to just be so frustrating that you give up before you can reach an actual human (since that is the point where there is a real cost to the company in giving you that support).
I'm not really sure LLMs have made it worse. They also haven't made it better, but it was already so awful that it just feels like a different flavor of awful.
1 reply →
Have you tried any of the leading open weight models, like GLM etc. And how does chatGPT or Gemini compare?
And kudos for refusing to use anything from the guy who's OK with his platform proliferating generated CSAM.
Giving Gemini a go after Opus did crap one time too many, and so far it seems that Gemini does better at identifying and fixing root causes, instead of piling code or disabling checks to hide the symptoms like Opus consistently seems to do.
I tried GLM 4.7 in Opencode today. In terms of capability and autonomy, it's about on par with Sonnet 3.7. Not terrible for a 10th the price of an Anthropic plan, but not a replacement.
[dead]
[flagged]
1 reply →
Making a new account and seeing doing the exact same thing to see if it happens again… would be against TOS and therefore is something you absolutely shouldn’t do
Claude shows me more than one personal account, as I registered via single signon and then - via e-mail, and I paid once only for one of them.
It’s effectively a multi-tenant interface.
I also used individual acc but on corp e-mail, previously.
You could generate a new multi-use CC in your vibe-bank app (as Revolut), buy burner (e) sim for sms (5 eur in NL); then rewrite all requests at your mitm proxy to substitute a device id to one, not derived from your machine.
But same device id, same phone could be perfectly legitimate use case: you registered on corp e-mail then you changed your work place, using the same machine.
or you lost access to your e-mail (what a pity)
But to get good use of it, someone should compose proper requests to ClickHouse or whatever they use, for logs, build some logic to run as a service or web hook to detect duplicates with a pipeline to act on it.
And a good percentage of flags wouldn’t have been ToC violations.
That’s a bad vibe, can you imagine how much trial and error prompting it requires?..
They can’t vibe the way though the claude code bugs alone, on time!
> Now even worse is Claude seemingly has no real support channel. You get their AI bot, and that's about it
This made me chuckle.
> I've been using it effectively to write software now (I am NOT a developer)
What have you found it useful for? I'm curious about how people without software backgrounds work with it to build software.
About my not having a software background, I started this as I've been a network/security/systems engineer/architect/consultant for 25 years, but never dev work. I can read and follow code well enough to debug things, but I've never had the knack to learn languages and write my own. Never really had to, but wanted to.
This now lets me use my IT and business experience to apply toward making bespoke code for my own uses so far, such as firewall config parsers specialized for wacky vendor cli's and filling in gaps in automation when there are no good vendor solutions for a given task. I started building my mcp server enable me to use agents to interact with the outside world, such as invoking automation for firewalls, switches, routers, servers, even home automation ideally, and I've been successful so far in doing so, still not having to know any code.
I'm sure a real dev will find it to be a giant pile of crap in the end, but I've been doing like applying security frameworks, code style guidelines using ruff, and things like that to keep it from going too wonky, and actually working it up to a state I can call it as a 1.0 and plan to run a full audit cycle against it for security audits, performance testing, and whatever else I can to avoid it being entirely craptastic. If nothing else, it works for me, so others can take it or not once I put it out there.
Even being NOT a developer, I understand the need for applying best practices, and after watching a lot of really terrible developers adjacent to me over the years make a living, think I can offer a thing or two in avoiding that as it is.
I started using claude-code, but found it pretty useless without any ability to talk to other chats. Claude recommended I make my own MCP server, so I did. I built a wrapper script to invoke anthropic's sandbox-runtime toolkit to invoke claude-code in a project with tmux, and my mcp server allows desktop to talk to tmux. Later I built in my own filesystem tools, and now it just spawns konsole sessions for itself invoking workers to read tasks it drops into my filesystem, points claude-code to it, and runs until it commits code, and then I have the PM in desktop verify it, do the final push/pr/merge. I use an approval system in a gui to tell me when claude is trying to use something, and I set an approve for period to let it do it's thang.
Now I've been using it to build on my MCP server I now call endpoint-mcp-server (coming soon to github near you), which I've modularized with plugins, adding lots more features and a more versatile qt6 gui with advanced workspace panels and widgets.
At least I was until Claude started crapping the bed lately.
what do you actually do besides build tools to build tools to build tools?
My use is considerably simpler than GP's but I use it anytime I get bogged down in the details and lose my way, just have Claude handle that bit of code and move on. Also good for any block of code that breaks often as the program evolves, Claude has much better foresight than I do so I replace that code with a prompt.
I enjoy programming but it is not my interest and I can't justify the time required to get competent, so I let Claude and ChatGPT pick up my slack.
I really don’t understand people that say claude has no human support. In the worst case the human version of their support got back to me two day after the AI, and they apologized for being so slow.
It really leads me to wonder if it’s just my questions that are easy, or maybe the tone of the support requests that go unanswered is just completely different.
They shorted me a day off credit on the first day of offering the 200+ subscription and it took me 6 weeks for a human to tell me "whoops well we'll fix that, cya."
I can't be alone . Literally the worst customer experience I've ever had with the most expensive personal dot com subscription I've ever paid for.
Never again. When Google sets the customer service bar there are MAJOR issues.
The desktop app is pretty terrible and super flaky, throwing vague errors all the time. Claude code seems to be doing much better. I also use it for non-code related tasks.
Have a max plan, didn't use it much the last few days. Just used it to explain me a few things with examples for a ttrpg. It just hanged up a few times.
Max plan and in average I use it ten times a day? Yeah, I am cancel. Guess they don't need me
That's about what I'm getting too! It just literally stops at some point, and any new prompt it starts, then immediately stops. This was even on a fairly short conversation with maybe 5-6 back and forth dialogs.
> Lately it's gotten entirely flaky, where chat's will just stop working
This happens to me more often than not both in the Claude Desktop and in web. It seems that longer the conversation goes the more likely it is to happen. Frustrating.
Judging by their status page riddled with red and orange as well as the months long degradation with blog post last Sept, it is not very reliable. If I sense it's responses are crap, I check the status page and low and behold usually it's degraded. For a non deterministric product, silent quality drops are pretty bad
It's amusing to observe that Claude works about as reliably as I'd expect for software written by Claude.
> where chat's will just stop working, simply ignoring new prompots, and otherwise go unresponsive
I had this start happening around August/September and by December or so I chose to cancel my subscription.
I haven't noticed this at work so I'm not sure if they're prioritizing certain seats or how that works.
I have noticed this when switching locations on my VPN. Some locations are stable and some will drop the connection while the response is streaming on a regular basis.
The Peets right next to the Anthropic office could be selling VPN endpoint service for quite the premium!
Serious question, why is codex and mistral(vibe) not a real alternative?
Codex: Three reasons. I've used all extensively, for multiple months.
Main one is that it's ~3 times slower. This is the real dealbreaker, not quality. I can guarantee that if tomorrow we woke up and gpt-5.2-codex became the same speed as 4.5-opus without a change in quality, a huge number of people - not HNers but everyone price sensitive - would switch to Codex because it's so much cheaper per usage.
The second one is that it's a little worse at using tools, though 5.2-codex is pretty good at it.
The third is that its knowledge cutoff is further in the past than both Opus 4.5 and Gemini 3 that it's noticeable and annoying when you're working with more recent libraries. This is irrelevant if you're not using those.
For Gemini 3 Pro, it's the same first two reasons as Codex, though the tool calling gap is even much bigger.
Mistral is of course so far removed in quality that it's apples to oranges.
Unpopular opinion but I prefer slow and correct.
My experience on Claude Max (still on it till end-of-month) has been frequent incomplete assignments and troubling decision making. I'll give you an example of each from yesterday.
1. Asked Claude to implement the features in a v2_features.md doc. It completed 8 of 10 but 3 incorrectly. I gave GPT-5.1-Codex-Max (high) the same tasks and it completed 10 of 10 but took perhaps 5-10x as long. Annoyingly, with LLM variability, I can't know for sure if I tried Claude again it would get it correct. The only thing I do know is that GTP-5.2 and 5.1 do a lot more "double-checking" both prior to executing and after.
2. I asked Claude to update a string being displayed in the UI of my app to display something else instead. The string is powered by a json config. Claude searched the code, somehow assumed it was being loaded by a db, did not find the json and opted to write code to overwrite whatever comes out of the 'db' (incorrect) to be what I asked for. This is... not desired behavior and the source of a category of hidden bugs that Claude has created in the past (other models do this as well but less often). Max took its time, found the source json file, and made the update in the correct place.
I can only "sit back and let an agent code" if I trust that it'll do the work right. I don't need it fast, I need it done right. It's already saving me hours where I can do other things in parallel. So, I don't get this argument.
That said, I have a Claude Max and OpenAI Pro subscription and use them both. I instead typically have Claude Opus work on UI and areas where I can visually confirm logic quickly (usually) and Codex in back-end code.
I often wonder how much the complexity of codebases affects how people discuss these models.
Have you tried lower reasoning levels?
1 reply →
The Claude models are still the best at what they do, right now GLM is just barely scratching sonnet 4.5 quality, mistral isnt really usable for real codebases and gemini is kind of in a weird spot where it's sometimes better then Claude at small targeted changes but randomly goes off the rails. Haven't tried codex recently but the last time I did the model thought for 27 minutes straight and then gave me about the same (incorrect) output that opus would have in 20 seconds. Anthropics models are their only moat as demonstrated by their cutting off of tools other then Claude code on their coding plans.
I tried codex, using my same sandbox setup with it. Normally I work with sonnet in code, but it was stuck on a problem for hours, and I thought hmm, let me try codex. Codex just started monkey patching stuff and broke everything within like 3-4 prompts. I said f-this, went back to my last commit, and tried Opus this time in code, which fixed the problem within 2 prompts.
So yeah, codex kinda sucks to me. Maybe I'll try mistral.
Gemini CLI is a solid alternative to Claude Code. The limits are restrictive, though. If you're paying for Max, I can't imagine Gemini CLI will take you very far.
Gemini CLI isn't even close to the quality of Claude Code as a coding harness. Codex and even OpenCode are much better alternatives.
Well, I use Gemini a lot (because it's one of three allowed families), but tbh it's pretty bad. I mean, it can get the job done but it's exhausting. No pleasure in using it.
Gemini CLI regularly gets stuck failing to do anything after declaring its plan to me. There seems to be no way to un-lock it from this state except closing and reopening the interface, losing all its progress.
Depending on task complexity, I like to write a small markdown file with the list of features or tasks. If I lose a session (with any model), I'll start with "we were disconnected, please review the desired features in 'features.md', verify current state, and complete anything remaining.
That has reliably worked for me with Gemini, Codex, and Opus. If you can get them to check-off features as they complete them, works even better (i.e, success criteria and an empty checkbox for them to mark off).
you should be able to copy the entire conversation and paste it in (including thinking/reasoning tokens).
When you have a conversation with an AI, in simple terms, when you type a new line and hit enter, the client sends the entire conversation to the LLM. It has always worked this way, and it's how "reasoning tokens" were first realized. you allow a client to "edit" the context, and the client deletes the hallucination, then says "Wait..." at the end of the context, and hits enter.
the LLM is tricked into thinking it's confused/wrong/unsure, and "reasons" more about that particular thing.
I tried Gemini like a year or so ago, and I gave up after it directly refused to write me a script and instead tried to tell me how to learn to code. I do not make this up.
That's at least two major updates ago. Probably worth another try.
2 replies →
Kilocode is a good alt as well. You can plug into OpenRouter or Kilocode to access their models.
Folks a solution might be to use the claude models inside the latest copilot. Copilot is good. Try it out. Latest versions improving all the time. You get plenty of usage at reasonable price.
One could, alternatively, come to the conclusion that the value of you as a customer far undersells the value of the product itself, even if it's doing what you expect it to do.
That is, you and most of claude users arn't paying the actual cost. You're like a Uber customer a decade ago.
[dead]