Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code is a slot machine

rgoldfinger.com

Post reply on HN
Print view View original

251–260 of 303 posts

Re: Claude Code is a slot machine

#251

Post by theshrike79 »

gonzalohm wrote: post #42

My experience with AI seems to be totally different than for most people. As an example, the other day asks chatgpt to write a configuration file for SQL fluff that formatted the code as an example that I provided. It proceeded to invent all the SQL fluff rules. And the ones that were actual rules were useless for the actual format that I wanted. I get it, SQLFluff rules are really confusing, but that's why I asked f…

There was a post somewhere that said if an AI invents a method or rule for something, it actually should be there. =)

It's a statistical prediction machine and it says your library should have a do_foo function. Is there a reason why it doesn't have one?

Re: Claude Code is a slot machine

#252

Post by prmph »

ChuckMcM wrote: post #195
astrobe_ wrote: post #48

Earlier quoted context omitted.

.. But the house always wins ?

Right? I hope that at some point the weights system will become clear enough that one could bias against wrong answers. Just “telling” it that is wrong biases for the current token cache and doesn’t back propagate to the model. Of course back propagating user input would be very exploitable so I don’t see that happening.

What about if further individualized training could occur at the user site?

Re: Claude Code is a slot machine

#253

Post by troupo »

danielbln wrote: post #244
troupo wrote: post #242

Earlier quoted context omitted.

And new problems appear. This remains a fact of life: https://news.ycombinator.com/item?id=44702776

Definitely, but isn't that progress? We solve problems and new problems appear, which we also solve. Rinse and repeat until the sun blows up.

> Definitely, but isn't that progress?

That is beside the point of the original comment

> We solve problems and new problems appear, which we also solve.

In AI space these are not new problems. These are the same "let's try this new magic incantation agains a non-deterministic black box".

Re: Claude Code is a slot machine

#254

Post by troupo »

leptons wrote: post #152
troupo wrote: post #37

Earlier quoted context omitted.

> But would these tools lose their magic if the results became completely deterministic? No. They would become extremely useful and more magical. Because instead of weird incantations and shamanic rituals of "just one more .rules file, bro, I swear" you could create useful reproducible working tools.

Except an LLM is not and never will be deterministic, by its very design that is not how it operates. It would need to be a fundamentally different tech from the ground up.

Exactly :)

Re: Claude Code is a slot machine

#255

Post by danielbln »

troupo wrote: post #253
danielbln wrote: post #244

Earlier quoted context omitted.

Definitely, but isn't that progress? We solve problems and new problems appear, which we also solve. Rinse and repeat until the sun blows up.

> Definitely, but isn't that progress? That is beside the point of the original comment > We solve problems and new problems appear, which we also solve. In AI space these are not new problems. These are the same "let's try this new magic incantation agains a non-deterministic black box".

Ok man, you do you. I'm over here making food use of this tooling, but it's not for everyone. Agree to disagree.

Re: Claude Code is a slot machine

#258

Post by Too »

dwaltrip wrote: post #193
eric-burel wrote: post #160

Can we collectively stop upvoting low quality 300 words random opinions about llm based dev? As a professional in the field I find the qualify of what's posted on HN really super low in this area, compared to posts eg related to cloud infrastructure or software engineering. There are better posts and sources than that.

The post may not have a ton of meat, but it resonates and seems ripe for discussion. It’s quite timely as we all try to figure out how and when to use these tools. Your comment doesn’t add much. Where’s the substance to your critique?

There are several topics like this on the front page every day, since many months back now, and the comments are all the same. It’s enough.

Re: Claude Code is a slot machine

#259

Post by th0ma5 »

brookst wrote: post #89
kregasaurusrex wrote: post #84

On Friday I was converting a constrained solver from python to another language, and ran into some difficulty with subsituting an optimzer that's a few lines of easily written Scipy; but barely being supported in another language. One AI tool found this out and fully re-implemented the solver using a custom linear algebra library it wrote from scratch. But another AI tool was really struggling with getting the right…

A very relatable experience. But not all that different from how humans work when in unfamiliar domains.

Except... Completely different

Re: Claude Code is a slot machine

#260

Post by th0ma5 »

theshrike79 wrote: post #249
moregrist wrote: post #179

Earlier quoted context omitted.

> One AI tool found this out and fully re-implemented the solver using a custom linear algebra library it wrote from scratch. So slow, untested, and likely buggy, especially as the inputs become less well-conditioned? If this was a jr dev writing code I’d ask why they didn’t use . Neither llm outcome seems very ideal to me, tbh.

With mathematical things you can always write comprehensive and complete unit tests to check the AIs work. TDD (and exhaustive unit tests in general) are a good idea with LLMs anyway. Just either tell it not to touch test, or in Claude's case you can use Hooks to _actually_ prevent it from editing any test file. Then shove it at the problem and it'll iterate a solution until the tests pass. It's like the Excel formul…

I think we all understand this we just don't think it works.
Post reply on HN