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

371–380 of 604 posts

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

#371

Post by CamperBob2 »

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…

Then hand over to Claude Sonnet.

Well, there's your problem. Why aren't you using the best tool for the job?

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

#373

Post by subscribed »

unshavedyak wrote: post #137
aleqs wrote: post #29

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?

It's something strange because i never have these issues. I often run two in parallel (though not all day), and generally have something running anytime i look at my laptop to advance the steps/tasks/etc. Usually i struggle to hit 50% on my Max20. Heck two weeks ago i tried my hardest to hit my limit just to make use of my subscription (i sometimes feel like i'm wasting it), and i still only managed to get to 80% for…

Maybe you should try running exactly the same prompts in exactly the same settings?

Chances are one of you has been drafted into an unpleasant experiment.

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

#374

Post by mceachen »

felixgallo wrote: post #200
wood_spirit wrote: post #178

Earlier quoted context omitted.

Yes that was one issue. It’s not the general degradation I have been talking about though, which is ongoing. I recall reading similar tales of woe with other providers here on HN. I think the gradual dialling back of capability as capacity becomes strained as users pile on is part of the MO of all the big AI companies.

the 'general degradation' is a myth. Check out https://isitnerfed.org/ .

Random crowd anecdata is still anecdata.

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

#375

Post by eweise »

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…

I give Claude small incremental tasks to do and it usually does them flawlessly. I know how to design the software and break into incremental tasks. Claude does the work. The productivity increase has been incredible. I think I'll be able to bootstrap a single person lifestyle business just using Claude.

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

#376

Post by scuderiaseb »

wg0 wrote: post #253
scuderiaseb wrote: post #228

Earlier quoted context omitted.

I must be doing something very different from everyone else, but I write what I want and how I want it and Opus 4.7 plans it for me, then I carefully review. Often times I need to validate and check things, sometimes I’ve revised the plan multiple times. Then implementation which I still use Opus for because I get a warning that my current model holds the cache so Sonnet shouldn’t implement. And honestly, I’m mostly…

>Then implementation which I still use Opus for because I get a warning that my current model holds the cache so Sonnet shouldn’t implement. This is based on the premise that given detailed plan, the model will exactly produce the same thing because the model is deterministic in nature which is NOT the case. These models are NOT deterministic no matter how detailed plan you feed it in. If you doubt, give the model sa…

> I do not know how you can do it on a Pro plan with Claude Opus 4.7 which is 7.5x more in terms of limit consumption and any small to medium size codebase would easily consume your limits in just the planning phase up to 50% in a single prompt

I also don’t understand because all I ever hear is people saying $100 Max plan is the minimum for serious work. I made 3-4 plans today, I’m familiar with the codebase and pointed the LLM in the direction where it needed to go. I described the functionality I wanted which wasn’t a huge rewrite, it touched like 4 files of which one was just a module of pydantic models. But one plan was 30% of usage and I had this over two sessions because I got a reset. I did read and understand everything line of code so that part takes me some time to do.

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

#377

Post by throwaway7783 »

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…

I don't know. I don't write detailed specs, but make it very iterative, with two sessions. One for coding and one for reviews at various levels.

Just the coding window makes mistakes, duplicates code, does not follow the patterns. The reviewer catches most of this, and the coder fixes them all after rationalizing them.

Works pretty well for me. This model is somewhat institutionalized in my company as well.

I use CC Opus 4.7 or Codex GPT 5.4 High (more and more codex off late).

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

#378

Post by rsanek »

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…

I'm confused. If you have detailed, specific expectations, why aren't using the best model available? Even if you were using Opus 4.7, I would inquire if you're using high/xhigh effort by default.

Feels crazy to me for people to use anything other than the best available.

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

#379

Post by janalsncm »

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…

How can a person reconcile this comment with the one at the root of this thread? One person says Claude struggles to even meet the strict requirements of a spec sheet, another says Claude is doing a great job and doesn’t even need specific specs?

I have my own anecdata but my comment is more about the dissonance here.

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

#380

Post by mathisfun123 »

_puk wrote: post #367
mathisfun123 wrote: post #362

Earlier quoted context omitted.

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 th…

> I find that the most galling thing about finding out about the thinking being discarded at cache clear

There's a really simple solution to this galling sensation: simply always keep in mind it's a stupid GenAI chat bot.

Post reply on HN