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

321–330 of 604 posts

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

#321

Post by joquarky »

echelon wrote: post #68
Someone1234 wrote: post #51

Earlier quoted context omitted.

It feels more and more like OpenAI/Anthoropic aren't the future but Qwen, Kimi, or Deepseek are. You can run them locally, but that isn't really the point, it is about democratization of service providers. You can run any of them on a dozen providers with different trade-offs/offerings OR locally. They won't ever be SOTA due to money, but "last year's SOTA" when it costs 1/4 or less, may be good enough . More quantit…

Open Source isn't even within 50% of what the SOTA models are. Benchmarks are toys, real world use is vastly different, and that's where they seriously lag. Why should anyone waste time on poorer results? I'd rather pay my $200/mo because my time matters. I'm not a poor college student anymore, and I need more return on my time. I'm not shitting on open weights here - I want open source to win. I just don't see how t…

What will you do when they stop burning cash and the $200 plan becomes $2000?

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

#322

Post by afro88 »

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. > That's vibecoding with an extra documentation step.

Read uncharitably, yeah. But you're making a big assumption that the writing of spec wasn't driven by the developer, checked by developer, adjusted by developer. Rewritten when incorrect, etc.

> You can still make the decisions, call the shots

One way to do this is to do the thinking yourself, tell it what you want it to do specifically and... get it to write a spec. You get to read what it thinks it needs to do, and then adjust or rewrite parts manually before handing off to an agent to implement. It depends on task size of course - if small or simple enough, no spec necessary.

It's a common pattern to hand off to a good instruction following model - and a fast one if possible. Gemini 3 Flash is very good at following a decent spec for example. But Sonnet is also fine.

> Stop trying to use it as all-or-nothing

Agree. Some things just aren't worth chasing at the moment. For example, in native mobile app development, it's still almost impossible to get accurate idiomatic UI that makes use of native components properly and adheres to HIG etc

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

#323

Post by ghurtado »

rafram wrote: post #271
Aurornis wrote: post #258

Earlier quoted context omitted.

> It’s pretty funny to claim that a model released 22 hours ago is the bare minimum requirement for AI-assisted programming. Not what I said. The OP was trying to write specs and have an AI turn it into an app, then getting frustrated with the amount of cleanup. If you want the AI to write code for you and minimize your cleanup work, you have to use the latest models available. They won't be perfect, but they're goin…

Is it actually the case that 5.5 is that much better at implementing specs than its very capable predecessor released a month ago? Just seems like a baseless and silly claim about a model that has barely been out long enough for anyone to do serious work with it.

> Is it actually the case that 5.5 is that much better

Nobody was talking about how much better it is until you wrote this though

It's like you're building your own windmills brick by brick

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

#324

Post by mlinsey »

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…

My anecdata is that it heavily depends on how much of the relevant code and instructions it can fit in the context window.

A small app, or a task that touches one clear smaller subsection of a larger codebase, or a refactor that applies the same pattern independently to many different spots in a large codebase - the coding agents do extremely well, better than the median engineer I think.

Basically "do something really hard on this one section of code, whose contract of how it intereacts with other code is clear, documented, and respected" is an ideal case for these tools.

As soon as the codebase is large and there are gotchas, edge cases where one area of the code affects the other, or old requirements - things get treacherous. It will forget something was implemented somewhere else and write a duplicate version, it will hallucinate what the API shapes are, it will assume how a data field is used downstream based on its name and write something incorrect.

IMO you can still work around this and move net-faster, especially with good test coverage, but you certainly have to pay attention. Larger codebases also work better when you started them with CC from the beginning, because it's older code is more likely to actually work how it exepects/hallucinates.

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

#325

Post by bigethan »

ramoz wrote: post #109
taytus wrote: post #102

Earlier quoted context omitted.

I'd recommend Kimi k2.6 for your use. It is an excellent model at a fraction of the cost, and you can use Claude Code with it. I did a 1:1 map of all my Claude Code skills, and it feels like I never left Opus. Super happy with the results.

What provider do you use for Kimi

OpenRouter and I'm toying around with Hermes. Seems good so far, but haven't really gotten into anything heavy yet. Though the "freedom" of not sweating the token pause and the costs not being too high is real.

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

#326

Post by duxup »

I’ve definitely encountered a drop in Claude quality.

Even a simple prompt focused on two files I told Claude to do a thing to file A and not change file B (we were using it as a reference).

Claude’s plan was to not touch file B.

First thing it did was alter file B. Astonishing simple task and total failure.

It was all of one prompt, simple task, it failed outright.

I also had it declare that some function did not have a default value and then explain what the fun does and how it defaults to a specific value….

Fundamentally absurd failures that have seriously impacted my level of trust with Claude.

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

#327

Post by _puk »

mathisfun123 wrote: post #307
teucris wrote: post #280

Earlier quoted context omitted.

But agents do keep task lists and check the tasks off as they go. Of course it’s not perfect either but it’s MUCH better than an LLM can offer on its own. If you are seeing an agent missing tasks, work with it to write down the task list first and then hold it accountable to completing them all. A spec is not a plan.

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?

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

#328

Post by buredoranna »

gwerbin wrote: post #225
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…

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…

> 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 "The Lord of the Rings". Even if it reproduces good chunks of the original, it does not devalue the original... in fact, I would argue, it enhances it.

Have I failed to take into account additional arguments and/or scenarios? Probably.

But, in my opinion, AI passes these tests. AI output is transformative, and in general, does not devalue the original.

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

#329

Post by tengbretson »

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…

> or even unnecessary code wrangling data (mapping objects into new objects of narrower types when won't be needed)

Dude! The amount of ad-hoc, interface-specific DTOs that LLM coding agents define drives me up the wall. Just use the damn domain models!

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

#330

Post by giancarlostoro »

drunken_thor wrote: post #22
giancarlostoro wrote: post #17

Earlier quoted context omitted.

You're using it within their high usage rate window. I hope you're aware of this, if you use it out of the high usage time window it's supposed to use less, but it does seem a little odd that Sonnet uses so much, even on Medium.

Ah so we are only supposed to use this work tool outside of work hours?

If you're on a personal tier, they prioritize those on the business tier yes.
Post reply on HN