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

491–500 of 604 posts

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

#491

Post by IcyWindows »

taikahessu wrote: post #486
IcyWindows wrote: post #454

Earlier quoted context omitted.

This kind of thinking seems like a road for people to have to pay a license for the rest of their life after going to school for the knowledge they "stole" from their textbooks.

Except the school paid royalties for that specific book. Every book. The money was distributed. Writers, publishers and so on. The normal stuff. Or if you had to buy the book yourself, same thing, distributed, royalties paid.

So your complaint is that they didn't pay for training data by buying every book found online?

That does seem more reasonable, but makes public libraries also evil.

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

#492

Post by DennisP »

janalsncm wrote: post #379
onlyrealcuzzo wrote: post #294

Earlier quoted context omitted.

> 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.

I just read Steve Yegge's book Vibe Coding, and he says learning to use AI effectively is a skill of its own, and takes about a year of solid work to get good at it. It will sometimes do a good job and other times make a mess, and he has a lot of tips on how to get good results, but also says a lot of it is just experience and getting a good feel for when it's about to go haywire.

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

#495

Post by ChicagoDave »

joquarky wrote: post #344
ChicagoDave wrote: post #296

I think there’s a clear split amongst GenAI developers. One group is consistently trying to play whack-a-mole with different models/tools and prompt engineering and has shown a sine-wave of success. The other group, seemingly made up of architects and Domain-Driven Design adherents has had a straight-line of high productivity and generating clean code, regardless of model and tooling. I have consistently advised all…

I kind of wonder if people with ADHD tend to fall into the latter group, as we are used to setting guardrails to keep us aligned to a goal.

ADHD may be a part of it but mentoring and some experience with TDD or strong unit testing is also a part.

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

#496

Post by ChicagoDave »

rglover wrote: post #331
ChicagoDave wrote: post #296

I think there’s a clear split amongst GenAI developers. One group is consistently trying to play whack-a-mole with different models/tools and prompt engineering and has shown a sine-wave of success. The other group, seemingly made up of architects and Domain-Driven Design adherents has had a straight-line of high productivity and generating clean code, regardless of model and tooling. I have consistently advised all…

Dead on. Any company not thinking about this like the 2nd group is setting themselves up for a bad time (and sadly, anecdotally, that seems to be an emerging majority).

Sadly, I agree that the majority are undisciplined.

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

#497

Post by ChicagoDave »

estimator7292 wrote: post #413
ChicagoDave wrote: post #296

I think there’s a clear split amongst GenAI developers. One group is consistently trying to play whack-a-mole with different models/tools and prompt engineering and has shown a sine-wave of success. The other group, seemingly made up of architects and Domain-Driven Design adherents has had a straight-line of high productivity and generating clean code, regardless of model and tooling. I have consistently advised all…

IME it seems that output quality is directly proportional to the amount of engineering effort you put in. If a bug happens and you just tell the model to fix it over and over with no critical thinking, you end up with an 800 line shell script meant to change the IP address on an interface (real example). If you stop and engage your brain to reason about bugs and explain the problem, the model can fix it in an accepta…

Even my guardrails can’t replace experience. You have to pay attention. This is exactly how some devs land in whack-a-mole loops.

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

#498

Post by fortynights »

lawrence1 wrote: post #213

The timeline doesn't make any sense. How can you subscribe a couple weeks ago and the problem start 3 weeks ago and yet things also went well for the first few weeks. was this written by GPT 5.5?

Seriously, I’ve been subscribed to Claude for 18 months now ($20/mo) during which time I’ve seen the hype around other models come and go in a matter of weekends. I’ve just come to accept that everyone is largely commodity and sometimes it’s worth taking a longer view (provided one can afford it).

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

#499

Post by tclancy »

oefrha wrote: post #484
janalsncm wrote: post #379

Earlier quoted context omitted.

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.

One aspect you have to consider is the differences in human beings doing the evaluation. I had a coworker/report who would hand me obvious garbage tier code with glaring issues even in its output, and it would take multiple iterations to address very specific review comments (once, in frustration, I showed a snippet of their output to my nontechnical mom and even my mom wtf’ed and pointed out the problem unprompted);…

This is magical because you are both on the exact right path and not right. My theory is there’s a sort of skill to teasing code from AI (or maybe not and it’s alchemy all over again) and this is all new enough and we don’t have a common vocabulary for it that it’s hard for one person who is having a good experience and one person who is not to meaningfully sort out what they are doing differently.

Alternatively, it could be there’s a large swath of people out there so stupid they are proud of code your mom can somehow review and suggest improvements in despite being nontechnical.

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

#500

Post by sameerds »

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…

> I can still run 2-3 clients almost 24/7 pumping out features.

Honest question. How does one do that? My workflow is to create one git worktree per feature and start one session per worktree. And then I spent two hours in a worktree talking to Opus and reviewing what it is doing.

Post reply on HN