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

561–570 of 604 posts

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

#561

Post by sidrag22 »

hunterpayne wrote: post #461
sidrag22 wrote: post #220

Earlier quoted context omitted.

> 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.

nah, you're kinda encapsulating what i viewed in my mind:

at what level of abstraction can you claim to actually "understand" the code?

You're claiming to understand down to the CMOS, but you are failing to even engage with what level understanding should be accepted. is "down to the CMOS" the bar? because then you're gonna be on an uphill battle as potentially the only human who traces a simple hello world python script down to it, because thats not how people develop software with high level languages.

is understanding the print()'s underlying code the bar? seems fairly gatekeepy, its kinda intuitive what a print does, everyone trusts its gonna do what its designed to do in the same way we trust the water that comes out of our faucets.

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

#562

Post by sarchertech »

SpaceNoodled wrote: post #558
riquito wrote: post #431

Earlier quoted context omitted.

Then you should expect any positive comment to be replied negatively by a competition's puppet or bot too

Not necessarily; rising tide and all that. When a new scam like this emerges, it behooves all of the grifters to cooperate and not muddy the waters with distrust.

I’m normally very skeptical of conspiracy theories. But saw an AI booster bot responding to a negative AI post I made here.

Someone pointed out to me in the comments that the username had posted long replies to 3 completely different threads in the same minute. That and looking back at its post history confirmed it was a bot.

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

#563

Post by janwillemb »

pmarsh wrote: post #487
janwillemb wrote: post #19

This is what worries me. People become dependent on these GenAI products that are proprietary, not transparant, and need a subscription. People build on it like it is a solid foundation. But all of a sudden the owner just pulls the foundation from under your building.

For the sake of argument if you build on AWS is that any more of a solid foundation? You're beholden to Amazon, unless you have the bandwidth to be able to DR immediately to another provider.

That is indeed a similar problem. Europe is now aware of this problem and starting to mitigate it, to reduce dependencies on big tech - how hard that may be.

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

#564

Post by sarchertech »

flyinglizard wrote: post #535
prmph wrote: post #529

Earlier quoted context omitted.

> they have encyclopedic knowledge at a superficial level, the approximate judgement and maturity of a teenager, and the short-term memory of a parakeet. If I ask for something, I get the statistical average opinion of a bunch of goons, unconstrained by context or common sense or taste. Love this paragraph; it's exactly how I feel about the LLMs. Unless you really know what you are doing, they will produce very sub-o…

Try asking to review your code as if it were Linus Torvalds. No, really.

I’ve tried that. I’ve experimented with a whole council of 13 personas including many famous developers. It’s definitely different. But it’s hasn’t performed significantly better in my tests.

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

#565

Post by sarchertech »

oops wrote: post #452
sarchertech wrote: post #433

Earlier quoted context omitted.

If you don’t have a very strong mental model for what you are working on Claude can very easily guide in you into building the wrong thing. For example I’m working on a huge data migration right now. The data has to be migrated correctly. If there are any issues I want to fail fast and loud. Claude hates that philosophy. No matter how many different ways I add my reasons and instructions to stop it to the context, it…

That’s interesting to hear as for me Claude has been quite good about writing code that fails fast and loud and has specifically called it out more than once. It has also called out code that does not fail early in reviews.

If you add a single space to a prompt, you’ll get a completely different output, so it’s no surprise that feeding entirely different programs into the prompt produces radically different output.

My guess is that there must be something about the language(go) or the domain (a data migration tool that uses Kafka) that triggers this.

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

#566

Post by sarchertech »

justinclift wrote: post #515
sarchertech wrote: post #433

Earlier quoted context omitted.

If you don’t have a very strong mental model for what you are working on Claude can very easily guide in you into building the wrong thing. For example I’m working on a huge data migration right now. The data has to be migrated correctly. If there are any issues I want to fail fast and loud. Claude hates that philosophy. No matter how many different ways I add my reasons and instructions to stop it to the context, it…

> it will constantly push me towards removing crashes and replacing them with “graceful error handling”. Is it generating JS code for that?

No this is a kafka consumer written in go.

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

#567

Post by sarchertech »

aforwardslash wrote: post #471
sarchertech wrote: post #433

Earlier quoted context omitted.

If you don’t have a very strong mental model for what you are working on Claude can very easily guide in you into building the wrong thing. For example I’m working on a huge data migration right now. The data has to be migrated correctly. If there are any issues I want to fail fast and loud. Claude hates that philosophy. No matter how many different ways I add my reasons and instructions to stop it to the context, it…

Have you created a plan where the requisite is not to bother you with x and y, and to use some predetermined approach? What you describe sometimes happens to me, but it happens less when its part of the spec.

Yes. That’s one of the things included in this.

> No matter how many different ways I add my reasons and instructions to stop it to the context

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

#568

Post by michaelmrose »

idiotsecant wrote: post #517
michaelmrose wrote: post #466

Earlier quoted context omitted.

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.

I'm assuming human creativity has intrinsic value, or what's the point of being human?

You are assuming that somehow human creativity was born with intellectual property and will somehow die with it. It's just not so.

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

#569

Post by mschulkind »

dragandj wrote: post #532
linsomniac wrote: post #445

Earlier quoted context omitted.

>Then hand over to Claude Sonnet. Have you tried Opus 4.6 with "/effort max" in Claude Code? That's pretty much all I use these days, and it is, honestly, doing a fantastic job. The code it's writing looks quite good to me. Doesn't seem to matter if it's greenfield or existing code. If code is harder to read than to write, you're doing yourself a disservice by having the output stage not be top shelf.

I find it works even better with "/effort ultra".

They renamed ultra to max about a week ago.

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

#570

Post by coldtea »

dieortin wrote: post #528
coldtea wrote: post #450

Earlier quoted context omitted.

> Might as well just write the code yourself at that point "We have this thing that can speed your code writing 10x" "If it isn't 1000x and it doesn't give me a turnkey end to end product might as well write the whole thing myself" People have forgotten balance. Which is funny, because the inability of the AI to just do the whole thing end to end correctly is what stands between 10 developers having a job versus 1 de…

Writing the code is usually not the bottleneck, so you don’t gain that much speeding it up. And as I said, you lose a lot of knowledge about the code when you don’t write it yourself. Unless coding is most of your job, which is rare, you’re giving up really knowing what your software does in order to achieve a very minor speed up. Just to end up having to spend way more time later trying to understand the AI generate…

>Writing the code is usually not the bottleneck

I hear this repeated often and it's false.

Writing the code is A bottleneck. Except if by "writing the code" people just mean the mere physical act of typing it in. Which is not what I mean.

But if someone thinks that just the design/architecture decisions take time, and the fleshing out in actual code does not, they're wrong.

Some coders seem to think they're high end architects, and the fleshing out the design is a triviallity that's very fast. Wathing high end coders wrote, e.g. in code session streams or just someone at your office, will show you it's never that fast.

In actual programming practice, even if you know the design end to end, even if it's a 100-line thing, writing it takes time.

Look up how to call those APIs you need. Debug when you inevitable got some of them wrong. Figure out that regex you need to write. Fix the 2-3 things you do wrong on the first pass of the "trivial" algorithm. Add some logic to catch and report errors and handle edge cases. Add tests.

All these are "trivial", but combined can take a couple of hours for something the AI will most of the time spit out correct the first time in a minute. And of course as you write you also explore dozens of decisions that could go either way, even with the same exact design and external interface to your code.

Getting that ready from the LLM within a minute means you can explore alternative designs, handle new issues that occured, add more functionality to make it more usable and smarter , etc, all the while you'd still be writing the original cruder version.

>Using AI is not a goal in itself, so I don’t care about “getting to use AI”. I care about doing my job as efficiently as possible, considering all parts of my job, not just coding.

Not the point. Nobody said AI is a goal in itself.

AI however does speed up the work, and if you take the black-and-white "if AI can't do it all by itself end-to-end without me intervening then I'd rather write everything myself" (what I respond to), then you're not doing your job "as efficiently as possible".

Post reply on HN