Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I cancelled Claude: Token issues, declining quality, and poor support

nickyreinert.de

Post reply on HN
Print view View original

361–370 of 604 posts

Re: I cancelled Claude: Token issues, declining quality, and poor support

#361

Post by system2 »

mwigdahl wrote: post #288
system2 wrote: post #54

Same here. The single prompt burnt all my tokens in 3 minutes for the day. What happened to Claude in the last 2 months? I was happy with what they were providing and was happy to pay whatever for it. Why did they mess with it? Why are they destroying the tool we all loved? I hate enshittification and I hate seeing this happening to Claude Code right now.

What level of subscription are you on? If you're complaining about running out of tokens but are happy to pay "whatever" for it, it should be Max 20x, yes? And one prompt drained all your tokens for the day on Max 20x?

I am on max 10x ($100 a month). I asked it to summarize a small codebase (2000 lines). Instead, it ran 4 agents in the background, and those agents went nuts, started reading everything and related dependencies, and sucked all my daily quota, forcing me to wait till 2 AM to continue using.

Up until last month, a $100 plan was more than enough, and it was difficult to run out of tokens per day for me. Something fundamentally changed, and Claude started making more mistakes and using more tokens. I know I am not tripping because I used it for over a year; this is absolutely new.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#362

Post by mathisfun123 »

_puk wrote: post #327
mathisfun123 wrote: post #307

Earlier quoted context omitted.

bro do you really not understand that that's a game played for your sake - it checks boxes yes but you have no idea what effect the checking of the boxes actually has. like do you not realize/understand that anthropic/openai is baking this kind of stuff into models/UI/UX to give the sensation of rigor.

Not to knee jerk on a bro comment, but, bro.. Are you seriously saying that breaking a large complex problem down into it's constituent steps, and then trying to solve each one of them as an individual problem is just a sensation of rigour?

I'm saying that's not what the stupid bot is actually doing, it's what anthropic added to the TUI to make you feel good in your feelies about what the bot is actually doing (spamming).

Edit: I'll give you another example that I realized because someone pointed it out here: when the stupid bot tells you why it fucked up, it doesn't actually understand anything about itself - it's just generating the most likely response given the enormous amount of pontification on the internet about this very subject...

Re: I cancelled Claude: Token issues, declining quality, and poor support

#363

Post by jonas21 »

wg0 wrote: post #262
Aurornis wrote: post #232

Earlier quoted context omitted.

Writing detailed specs and then giving them to an AI is not the optimal way to work with AI. That's vibecoding with an extra documentation step. Also, Sonnet is not the model you'd want to use if you want to minimize cleanup. Use the best available model at the time if you want to attempt this, but even those won't vibecode everything perfectly for you. This is the reality of AI, but at least try to use the right mod…

> Writing detailed specs and then giving them to an AI is not the optimal way to work with AI. It is NOT the way to work with humans basically because most software engineers I worked with in my career were incredibly smart and were damn good at identifying edge cases and weird scenarios even when they were not told and the domain wasn't theirs to begin with. You didn't need to write lengthy several page long Jira ti…

> That's why every chat box has that "Regenerate" button.

Wait, are you doing this in the web chat interface?!

That's definitely not a good way. You need to be using a harness (like Claude Code) where the agent can plan its work, explore the codebase, execute code, run tests, etc. With this sort of set up, your prompts can be short (like 1 to 5 sentences) and still get great results.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#364

Post by brachkow »

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?

Re: I cancelled Claude: Token issues, declining quality, and poor support

#365

Post by gverrilla »

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.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#366

Post by ForOldHack »

Aurornis wrote: post #232
wg0 wrote: post #202

I write detailed specs. Multifile with example code. In markdown. Then hand over to Claude Sonnet. With hard requirements listed, I found out that the generated code missed requirements, had duplicate code or even unnecessary code wrangling data (mapping objects into new objects of narrower types when won't be needed) along with tests that fake and work around to pass. So turns out that I'm not writing code but I'm r…

Writing detailed specs and then giving them to an AI is not the optimal way to work with AI. That's vibecoding with an extra documentation step. Also, Sonnet is not the model you'd want to use if you want to minimize cleanup. Use the best available model at the time if you want to attempt this, but even those won't vibecode everything perfectly for you. This is the reality of AI, but at least try to use the right mod…

"Writing detailed specs and then giving them to an AI is not the optimal way to work with AI." Perfect. I loosely define things, and then correct it, and tell it to make the corrections, and it gets trained, but you have to constantly watch it. Its like a glorified auto-typer.

"Ignore all of the LinkedIn and social media hype about prompting apps into existence." Absolutely, its not hype, its pure marketing bullshitzen.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#367

Post by _puk »

mathisfun123 wrote: post #362
_puk wrote: post #327

Earlier quoted context omitted.

Not to knee jerk on a bro comment, but, bro.. Are you seriously saying that breaking a large complex problem down into it's constituent steps, and then trying to solve each one of them as an individual problem is just a sensation of rigour?

I'm saying that's not what the stupid bot is actually doing, it's what anthropic added to the TUI to make you feel good in your feelies about what the bot is actually doing (spamming). Edit: I'll give you another example that I realized because someone pointed it out here: when the stupid bot tells you why it fucked up, it doesn't actually understand anything about itself - it's just generating the most likely respon…

I'm not disagreeing in principle, but the detritus left after an anthropic outage is usually quite usable in a completely fresh session. The amount of context pulled and stored in the sandbox is quite hefty.

Whist I can't usually start from the exact same point in the decisioning, I can usually bootstrap a new session. It's not all ephemeral.

To your edit: I find that the most galling thing about finding out about the thinking being discarded at cache clear. Reconstruction of the logical route it took to get to the end state is just not the same as the step by step process it took in the first place, which again I feel counters your "feelies".

Re: I cancelled Claude: Token issues, declining quality, and poor support

#368

Post by Someone1234 »

vlovich123 wrote: post #110
Someone1234 wrote: post #86

Earlier quoted context omitted.

> Open Source isn't even within 50% of what the SOTA models are. When was the last time you used any of them? Because, a lot of people are actively using them for 9-5 work today, I count myself in that group. That opinion feels outdated, like it was formed a year ago+ and held onto. Or based on highly quantized versions and or small non-Thinking models. Do you really think Qwen3.6 for a specific example is "50%" as g…

Qwen3.6 at which model size and quantization? I already think Opus 4.6 is usable but still dumb as bricks. A 20% cut off that feels like it would still be unusable. And that's not even getting to the annoyance of setting everything up to run locally & getting HW that can run it locally which basically looks like a Macbook M4 these days as the x86 side is ridiculously pricey to get decent performance out of models.

At their highest model size and quant. We are discussing price and quality at the top, not what you can run on the lower end.

So the starting point is Opus 4.7 pricing and we're contrasting alternatives near the top end (offered across multiple providers).

Also I said 20% was hyperbole, meaning far too high.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#369

Post by ragequittah »

taikahessu wrote: post #343
buredoranna wrote: post #328

Earlier quoted context omitted.

> the whole thing being built on copyright infringement I am not a lawyer, but am generally familiar with two "is it fair use" tests. 1. Is it transformative? I take a picture, I own the copyright. You can't sell it. But if you take a copy, and literally chop it to pieces, reforming it into a collage, you can sell that. 2. Does the alleged infringing work devalue the original? If I have a conversation with ai about "…

In order for LLM to be useful, you need to copy and steal all of the work. Yes, you can argue you don't need the whole work, but that's what they took and feed it in. And they are making money off of other people's work. Sure, you can use mental jiujutsu to make it fair use. But fair use for LLMs means you basically copy the whole thing. All of it. It sounds more like a total use to me. I hope the free market and tec…

I always wonder if anyone out there thinks they're not making money off of other people's work. If you're coding, writing a fantasy novel, taking a photograph or drawing a picture from first principals you came up with yourself I applaud you though.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#370

Post by prmph »

onlyrealcuzzo wrote: post #294
gwerbin wrote: post #225

Earlier quoted context omitted.

Or just don't use AI to write code. Use it as a code reviewer assistant along with your usual test-lint development cycle. Use it to help evaluate 3rd party libraries faster. Use it to research new topics. Use it to help draft RFCs and design documents. Use it as a chat buddy when working on hard problems. I think the AI companies all stink to high heaven and the whole thing being built on copyright infringement stil…

> Or just don't use AI to write code. Anecdata, but I'm still finding CC to be absolutely outstanding at writing code. It's regularly writing systems-level code that would take me months to write by hand in hours, with minimal babysitting, basically no "specs" - just giving it coherent sane direction: like to make sure it tests things in several different ways, for several different cases, including performance, comp…

But, how do you know the code is good?

If you do spot checks, that is woefully inadequate. I have lost count of the number of times when, poring over code a SOTA LLM has produced, I notice a lot of subtle but major issues (and many glaring ones as well), issues a cursory look is unlikely to pick up on. And if you are spending more time going over the code, how is that a massive speed improvement like you make it seem?

And, what do you even mean by 10x the amount of work? I keep saying anybody that starts to spout these sort of anecdotes absolutely does NOT understand real world production level serious software engineering.

Is the model doing 10x the amount of simplification, refactoring, and code pruning an effective senior level software engineer and architect would do? Is it doing 10x the detailed and agonizing architectural (re)work that a strong developer with honed architectural instincts would do?

And if you tell me it's all about accepting the LLM being in the driver's seat and embracing vibe coding, it absolutely does NOT work for anything exceeding a moderate level of complexity. I used to try that several times. Up to now no model is able to write a simple markdown viewer with certain specific features I have wanted for a long time. I really doubt the stories people tell about creating whole compilers with vide coding.

If all you see is and appreciate that it is pumping out 10x features, 10x more code, you are missing the whole point. In my experience you are actually producing a ton of sh*t, sorry.

Post reply on HN