alt Hacker NewsI cancelled Claude: Token issues, declining quality, and poor support
Comments
It's bad, really bad.
The filesystem tool cannot edit xml files with <name></name> elements in it
I've been very happy using Codex in the VScode extension. Very high quality coding and generous token limits. I've been running Claude in the CLI over the last couple of months to compare and overall I prefer Codex, but would be happy with either.
Sometimes it feels like Anthropic uses token processing as a throttling tool, to their advantage.
Signup for all major providers (pro plan) and round-robin between all of them. This is the only way to protect against not having access to all of these heavily subsidised subscriptions. See what happened to Copilot.
If someone wants to move off Claude what are the alternatives? More importantly can another system pick up from where Claude left off or is there some internal knowledge Claude keeps in their configuration that I need to extract before canceling?
I have enterprise plans for all AI services except Google. GitHub Copilot in VS Code is the best I have used so far. I hear a lot of complaints from people who are holding it wrong. In a single day I can have a beautiful greenfield app deployed. One dev. One day. Something that would have taken weeks with two teams bumping into each other. It's fully documented. Beautiful code. I read the reasoning prompts as it flows by to get an idea of what is going on. I work in phases and review the code and working product quickly after that. Minimal issues.
I'm an executive, the devs complaining are getting retrained or put on the chopping block.
My rockstars are now random contractor devs from Vietnam. The aloof FTE grey beards saying "I don't know, it doesn't work very good on X." Are getting a talking to or being sidelined/canned. So far most of my grey beards are adapting pretty well.
I'm not waiting on people to write code any more. No way in hell.
Seems like some of the token issues may be corrected now
Biggest issue i see is, models are not getting efficient. This is no where going to get commoditised. There will be a limit at which you can burn money at subsidised cost.
As many others I had negative (not good as before) feeling about Claude Code lately
What I don't understand is these loud "voting with money" comments. What they are canceling is very subsidized plan to buy something that delivers a lot of value.
There are only two providers that can provide this level of models at very subsidized price - anthropic and openai. Both of them are bad in terms of reliability.
So I wonder what these people do after they "cancel" both of them? Do they see producing less result at same hourly rate as everyone else on the market as viable option?
I've see a post like this every week for the last 2 years. Are these models actually getting worse? Or do folks start noticing the cracks as they use them more and more?
I use Claude Code with GLM, Kimi and MiniMax models. :)
I was worried about Anthropic models quality varying and about Anthropic jacking up prices.
I don't think Claude Code is the best agent orchestrator and harness in existence but it's most widely supported by plugins and skills.
I'm torn because I use it in my spare time, so I've missed some of these issues, I don't use it 9 to 5, but I've built some amazing things, when 1 Million tokens dropped, that was peak Claude Code for me, it was also when I suspect their issues started. I've built up some things I've been drafting in my head for ages but never had time for, and I can review the code and refine it until it looks good.
I'm debating trying out Codex, from some people I hear its "uncapped" from others I hear they reached limits in short spans of time.
There's also the really obnoxious "trust me bro" documentation update from OpenClaw where they claim Anthropic is allowing OpenClaw usage again, but no official statement?
Dear Anthropic:
I would love to build a custom harness that just uses my Claude Code subscription, I promise I wont leave it running 24/7, 365, can you please tell me how I can do this? I don't want to see some obscure tweet, make official blog posts or documentation pages to reflect policies.
Can I get whitelisted for "sane use" of my Claude Code subscription? I would love this. I am not dropping $2400 in credits for something I do for fun in my free time.
I used Opus via Copilot until December and then largely switched over to Claude Code. I'm not sure what the difference is but I haven't seen any of these issues in daily use.
Switched to local models after quality dropped off a cliff and token consumption seemed to double. Having some success with Qwen+Crush and have been more productive.
Off topic: I do feel like this model switching content feels very circa 2010 "I'm quitting Facebook"
I hope codex doesn’t decline the same way
I’m blown away by how good it is lately
i ran prompts used up a ton of usage, and got no return just showed error.
Asked support hey i got nothing back i tried prompting several times used a ton of usage and it gave no response. I'd just like usage back. What I payed for I never got.
Just bot response we don't do refunds no exceptions. Even in the case they don't serve you what your plan should give you.
If all Claude does is automate mundane code, why not just make a "meta library" of said common mundane code snippets?
The usage metering is just so incredibly inconsistent, sometimes 4 parallel Opus sessions for 3 hours straight on max effort only uses up 70% of a session, other times 20 mins / 3 prompts in one session completely maxes it out. (Max x20 plan) Is this just a bug on anthropic side or is the usage metering just completely opaque and arbitrary?
We are in the 'we need to IPO so screw our customers' phase of the cycle
I don't get it. I use Claude Code every day, what I would consider pretty heavy usage...at least as heavy as I can use it while actually paying attention to what it's producing and guiding it effectively into producing good software. I literally never run into usage limits on the $100 plan, even when the bugs related to caching, etc. were happening that led to inflated token usage.
WTF are y'all doing that chews tokens so fast? I mean, sure, I could spin up Gas Town and Beads and produce infinite busy work for the agents, but that won't make useful software, because the models don't want anything. They don't know what to build without pretty constant guidance. Left to their own devices, they do busy work. The folks who "set and forget" on AI development are producing a whole lot of code to do nothing that needed doing. And, a lot of those folks are proud of their useless million lines of code.
I'm not trying to burn as many tokens as a possible, I'm trying to build good software. If you're paying attention to what you're building, there's so many points where a human is in the loop that it's unusual to run up against token limits.
Anyway, I assume that at some point they have to make enough money to pay the bills. Everything has been subsidized by investors for quite some time, and while the cost per token is going down with efficiency gains in the models/harnesses and with newer compute hardware tuned for these workloads, I think we're all still enjoying subsidized compute at the moment. I don't think Anthropic is making much profit on their plans, especially with folks who somehow run right at the edge of their token limit 24/7. And, I would guess OpenAI is running an even lossier balance sheet (they've raised more money and their prices are lower).
I dunno. I hear a lot of complaining about Claude, but it's been pretty much fine for me throughout 4.5, 4.6 and 4.7. It got Good Enough at 4.5, and it's never been less than Good Enough since. And, when I've tried alternatives, they usually proved to be not quite Good Enough for some reason, sometimes non-technical reasons (I won't use OpenAI, anymore, because I don't trust OpenAI, and Gemini is just not as good at coding as Claude).
When I saw the German screenshot it all made sense to me.
anyone remember the whole “delete uber” thing from 2017ish? good times
Waiting 60s every time I send a msg really kills the ux of claude
4.7 is the breaking point for me
It's almost unusable
Yeah, session limits are kinda show stoppers.
Did the same with Google Ai Ultra. They rug pulled the subscribers. They changed the deal, we cancel. Simple.
I just cancelled my Max20 plan yesterday.
It also seems to me they route prompts to cheaper dumber models that present themselves as e.g. Opus 4.7. Perhaps that's what is "adaptive reasoning" aka we'll route your request to something like Qwen saying it's Opus. Sometimes I get a good model, so I found I'll ask a difficult question first and if answer is dumb, I terminate the session and start again and only then go with the real prompt. But there is no guarantee model will be downgraded mid session. I wish they just charged real price and stopped these shenanigans. It wastes so much time.
Same, it's a mess.
This sounds just like all my neighbors complaining about their internet provider.
Very similar experience, although I didn’t use claude for anything in production, but I did try some tests with some few topics and questions on things that I know, and while initially it works very well, but as soon as you dive deeper you get all sort of extra none sense that was never asked to add/do nor it’s useful, just workarounds after workarounds after duct tape solutions, several times I would say “no, why are you introducing xyz, that will cause this and that” to get similar answer of “thanks for pushing back, you are right bla bla”.
We probably hit peak generative AI last year, now they probably use AI to improve the AI so it’s kinda garbage in garbage out, or maybe anthropic is deprioritizing users while favoring enterprise or even government where it provides better quality for higher contracts.
Codex is becoming such a good product. I have the 100$ pro lite. I have Claude still but 20$. I rarely use it. Let’s see if they give generous limits and more importantly a model that’s better than 5.5. The mythos fear mongering did not give me a good impression that they care about the average developer.
It's not magic but for me definitly claude is the way to go. Not expecting magic it's just another level of non-slop than the rest I've tried.
Maybe this is an unpopular opinion, but I think choosing which companies to support during this period of pre-alignment is one way to vote which direction this all goes. I'm happy to accept a slightly worse coding agent if it means I don't get exterminated someday.
Imagine vibe coding your core consumer application and associated backend…
Oh wait, I don’t have to imagine. That’s what Anthropic does. A nice preview for what is in store for those who chose to turn off their brains and turn on their AI agents.
I cancelled in the minute my subscription stopped working in Pi. Not going back to the slopfest what Claude Code is.
My main problem with claude code right now is observability. I've been experimenting a lot with vibe coding, but nowadays I can't even tell what it's doing. It's still delivering me value, but the trust on the company is going down and I've already started looking for alternatives.
AI has a lot of future potential but at every level... it's still not very good. And certainly not good enough to validate the expense, let alone what the actual cost would be were it profitable.
Anthropic is astroscaling. We're essentially buying into a loop where speed and iteration take precedence over stability and support. If you view them as an experimental lab undergoing rapid atmospheric friction rather than a company, the "unreliability" is just the cost of being at the frontier. This is not an endorsement for Anthropic, just imagining their craziness on how you "can" grow in a fraction of time.
Those AI using software developers begin to show signs of addiction:
From "yay, claude is awesome" to "damn, it sucks". This is like with withdrawal symptoms now.
My approach is much easier: I'll stay the oldschool way, avoid AI and come up with other solutions. I am definitely slower, but I reason that the quality FOR other humans will be better.
I have token issues three times a day, and I just upgraded to pro... and now this... now I cancel. my work flow was co-pilot to Gemini to Claude Code... and the bottle neck was always CC. Always. I am done. It should be pretty easy to replace CC.
AI used to be, the punched card replicator... its all replaceable.
The midwit curve of LLMs has OpenAI on both ends.
Me too.
I just noticed today that it doesn't warn about approaching limits and just blows straight into billing extra tokens.
I'm pretty sure it used to warn when you got close to your 5hr limit, but no, it happily billed extra usage. Granted only about $10 today, but over the span of like 45 minutes. Not super pleased.
Cool
We can't do it. We standardized. They got us.
absolute garbage support was the reason why I canceled. who would have thought that an AI company has only bots as support agents
I feel like Anthropic is forcing their new model (Opus 4.7) to do much less guess work when making architectural choices, instead it prefers to defer back decisions to the user. This is likely done to mine sessions for Reinforcement-Learning signals which is then used to make their future models even smarter.