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

461–470 of 604 posts

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

#461

Post by hunterpayne »

sidrag22 wrote: post #220
raincole wrote: post #183

Earlier quoted context omitted.

> the day when LLM-assisted coding is commoditized Like yesterday? LLM-assisted coding is $100/mo. It looks very commoditized when most houses in developed world pay more for electricity than that. My definition of LLM-assisted coding is that you fully understand every change and every single line of the code. Otherwise it's vibe coding. And I believe if one is honest to this principle, it's very hard to deplete the…

> fully understand every change and every single line of the code. im probably just not being charitable enough to what you mean, but thats an absurd bar that almost nobody conforms to even if its fully handwritten. nothing would get done if they did. But again, my emphasis is on that im probably just not being charitable to what you mean.

I do. If you don't, maybe you shouldn't be writing software professionally. And yes, I've written both DBs and compilers so I do understand what is happening down to the CMOS. I think what you are doing is just cope.

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

#462

Post by hunterpayne »

adastra22 wrote: post #311
BowBun wrote: post #306

Earlier quoted context omitted.

In industry, the cost is more than 100/mo for engineers. With increased adoption and what I know now, I expect full time devs to rack up $500-$2000 usage bills if they're going full parallel agentic dev. Personal usage for projects and non-production software is not a benchmark IMO

I routinely use $4k to $5k worth of tokens a month on my $200/mo Max subscription. I don't even code every day. You can use a Max subscription for work, btw.

You do understand the concept of a subsidy right?

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

#463

Post by zdragnar »

derektank wrote: post #265
sdevonoes wrote: post #44

Earlier quoted context omitted.

The sooner you cancel the sooner you become independent of them

You could say the same thing about your mobile phone bill. Most people still consider the benefits of roaming access to the internet greater than the downsides of being dependent on it.

There's very few, if any, alternatives to roaming internet access.

AI tools... do what you already do, sometimes faster, sometimes worse, usually both depending on the task.

There's a massive gap of necessity between them.

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

#464

Post by Someone1234 »

vlovich123 wrote: post #393
Someone1234 wrote: post #368

Earlier quoted context omitted.

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.

That makes no sense because the largest Qwen models are not even open weight so I’m not sure how that’s any different.

Right, which isn't what we're discussing, since I mentioned "across multiple providers" in every comment about this topic.

Those closed weight models aren't available like we're discussing. They're only available from the vendor that created them.

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

#465

Post by michaelmrose »

phatskat wrote: post #359
ghurtado wrote: post #314

Earlier quoted context omitted.

> basically no "specs" - just giving it coherent sane direction This is one variable I almost always see in this discussion: the more strict the rules that you give the LLM, the more likely it is to deeply disappoint you The earlier in the process you use it (ie: scaffolding) the more mileage you will get out of it It's about accepting fallability and working with it, rather than trying to polish it away with care

To me this still feels like it would be a net negative. I can scaffold most any project with a language/stack specific CLI command or even just checking out a repo. And sure, AI could “scaffold” further into controllers and views and maybe even some models, and they probably work ok. It’s then when they don’t, or when I need something tweaked, that the worry becomes “do I really understand what’s going on under the h…

A lot of the benefit of scaffolding is building basic context which you can also build by feeding it the files produced by whatever CLI tool and talk about it forcing it to think for lack of a better word about your design. You can also force feed it design and api documentation. If you think that you have given it too much you are almost certainly wrong.

Doing nonsensical things with a library feed it the documentation still busted make it read the source

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

#466

Post by michaelmrose »

idiotsecant wrote: post #391
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 "…

This is a tiresome and well trod road. The fact of the matter is that for profit corporations consumed the sum knowledge of mankind with the intent to make money on it by encoding it into a larger and better organized corpus of knowledge. They cited no sources and paid no fees (to any regular humans, at least). They are making enormous sums of money (and burning even more, ironically) doing this. If that doesn't viol…

You are assuming intellectual property has intrinsic basis when it's at best functional not foundational. It's only useful if the net value to society is positive which is extremely dubious.

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

#467

Post by baranul »

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…

Now that there is Claw Code[1], seems like many of these cancellations are easier to do.

[1]: https://github.com/ultraworkers/claw-code

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

#468

Post by reddozen »

VertanaNinjai wrote: post #436
thepasch wrote: post #338

Earlier quoted context omitted.

> They changed it do all of the changes in a virtual cloud environment, then dump the final result at the end of the response. That’s a hallucination. All they did was hide thinking by default. Quick Google search should easily teach you how to turn it back on (I literally have it enabled in my harness).

Is anything that might be wrong or misinformation now a “hallucination”?

Can you blame them for believing thinking tokens are completely hidden now? Anthropic has changed the way to see it 3 times in 3 months with no warnings or visible upgrade path. First it was shown by default, then you had to press control+o, then control+t, then it got locked behind a settings.json, then you had to manually enable with --verbose, now it's some random ENV var.

Whoever is their product manager should be embarrassed at the UX they provide.

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

#469

Post by NewsaHackO »

Madmallard wrote: post #428
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 "…

What in the mental gymnastics? They just stole everyone's hard work over decades to make this or it wouldn't have been useful at all.

That's a statement. The comment you are replying to had actual reasoning behind his claim. Do you have any actual reasoning behind yours?

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

#470

Post by aforwardslash »

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.

It boils down to scope. I use CC in both very specific one-language systems and broad backend-frontend-db-cache systems. You can guess where the difficulty lies. (Hint: its the stuff with at least 3 distinct languages)
Post reply on HN