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

Reports of code's death are greatly exaggerated

stevekrouse.com

Post reply on HN
Print view View original

191–200 of 486 posts

Re: Reports of code's death are greatly exaggerated

#191

Post by skissane »

lateforwork wrote: post #71

Chris Lattner, inventor of the Swift programming language recently took a look at a compiler entirely written by Claude AI. Lattner found nothing innovative in the code generated by AI [1]. And this is why humans will be needed to advance the state of the art. AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. AI…

> Chris Lattner, inventor of the Swift programming language recently took a look at a compiler entirely written by Claude AI. Lattner found nothing innovative in the code generated by AI [1]. And this is why humans will be needed to advance the state of the art.

Lots of people have ideas for programming languages; some of those ideas may be original-but many of those people lack the time/skills/motivation to actually implement their ideas. If AI makes it easier to get from idea to implementation, then even if all the original ideas still come from humans, we still may stand to make much faster progress in the field than we have previously.

Re: Reports of code's death are greatly exaggerated

#193

Post by ehsanu1 »

js8 wrote: post #145
lateforwork wrote: post #71

Chris Lattner, inventor of the Swift programming language recently took a look at a compiler entirely written by Claude AI. Lattner found nothing innovative in the code generated by AI [1]. And this is why humans will be needed to advance the state of the art. AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. AI…

> AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. Of course! But that's what makes them so powerful. In 99% of cases that's what you want - something that is conventional. The AI can come up with novel things if it has an agency, and can learn on its own (using e.g. RL). But we don't want that in most use cases…

That shows it knew this bit of satire more than anything. Also, the problem as stated isn't actually constrained enough to be unsolvable: https://youtu.be/B7MIJP90biM

Re: Reports of code's death are greatly exaggerated

#194

Post by sally_glance »

chongli wrote: post #180
sally_glance wrote: post #177

Earlier quoted context omitted.

Can we be sure? Maybe it's just very rare for experience, education and memories to line up in exactly the way that allows synthesizing something innovative. So it requires a few billion candidates and maybe a couple of generations too.

I want to point back to my remark about everyday people. if you don't limit yourself to "advancing the state of the art at the far frontiers of human knowledge" but allow for ordinary people to make everyday contributions in their daily lives, you get even more This isn't a throwaway comment. I do this all the time myself, at work. Everywhere I've worked, I do this. I challenge the assumptions and try to make things…

Experimentation leads to experience, so I feel like this was included by the parent comment. And in the case of writing software, agents are able to experiment today. They run tests, check log output, search DBs... Sure, they can't have apples fall on their heads like Newton had but they can totally observe the apple falling on someones head in a video.

Re: Reports of code's death are greatly exaggerated

#196

Post by thunky »

sheeshkebab wrote: post #150
thunky wrote: post #144

Earlier quoted context omitted.

> Claude AI. Lattner found nothing innovative in the code generated by AI [1]. And this is why humans will be needed to advance the state of the art And yet the AI probably did better than 99% of human devs would have done in a fraction of the time.

Human devs rarely need to create compilers. Those that do would do much better job. what’s your point again?

The point is that saying the LLM failed to do what the overwhelming majority of devs can't do isn't exactly damning.

It's like Stephen King saying an AI generated novel isn't as good as his. Fine, but most of have much lesser ambitions than topping the work of the most successful people in the field.

Re: Reports of code's death are greatly exaggerated

#197

Post by js8 »

ehsanu1 wrote: post #193
js8 wrote: post #145

Earlier quoted context omitted.

> AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. Of course! But that's what makes them so powerful. In 99% of cases that's what you want - something that is conventional. The AI can come up with novel things if it has an agency, and can learn on its own (using e.g. RL). But we don't want that in most use cases…

That shows it knew this bit of satire more than anything. Also, the problem as stated isn't actually constrained enough to be unsolvable: https://youtu.be/B7MIJP90biM

Feel free to ask Claude about any other contradictory request. I use Claude Code and it often asks clarifying questions when it is unsure how to implement something, or or autocorrects my request if something I am asking for is wrong (like a typo in a filename). Of course sometimes it misunderstands; then you have to be more specific and/or divide the work into smaller pieces. Try it if you haven't.

Re: Reports of code's death are greatly exaggerated

#198

Post by thunky »

coldtea wrote: post #165
kstrauser wrote: post #19

Earlier quoted context omitted.

That’s factually untrue. I’m using models to work on frameworks with nearly zero preexisting examples to train on, doing things no one’s ever done with them, and I know this because I ecosystem around these young frameworks. Models can RTFM (and code) and do novel things, demonstrably so.

> I’m using models to work on frameworks with nearly zero preexisting examples to train on Zero preexisting examples of your particular frameworks . Huge number of examples of similar existing frameworks and code patterns in their training set though. Still not a novel thing in any meaningful way, not any more than someone who has coded in dozens of established web frameworks, can write against an unfamiliar to them…

> Still not a novel thing in any meaningful way

Right. What you're saying is that barely anyone is doing truly novel work. 100% agree.

Re: Reports of code's death are greatly exaggerated

#199

Post by storus »

pacman128 wrote: post #16

In a chat bot coding world, how do we ever progress to new technologies? The AI has been trained on numerous people's previous work. If there is no prior art, for say a new language or framework, the AI models will struggle. How will the vast amounts of new training data they require ever be generated if there is not a critical mass of developers?

There is even a bigger problem; if AI didn't see your framework, you don't exist. Soon AI companies will be asking for money from devs to include their frameworks in the training dataset. Worse than Google's SEO that could at least be gamed somewhat.

Re: Reports of code's death are greatly exaggerated

#200

Post by js8 »

sally_glance wrote: post #175
js8 wrote: post #145

Earlier quoted context omitted.

> AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. Of course! But that's what makes them so powerful. In 99% of cases that's what you want - something that is conventional. The AI can come up with novel things if it has an agency, and can learn on its own (using e.g. RL). But we don't want that in most use cases…

You had me at "fuzzy", but lost me at "clean up" - because that's what I usually have to do after it went on another wild refactoring spree. It's a stochastic thing, maybe you're lucky and it fuzzy-matches exactly what you want, maybe the distributions lead it astray. On the line test, I guess it's highly probable that the joke and a few hundred discussions or blog pieces about it were in it's training data.

I only have experience with Claude Code. If it goes on a spree, the task you are giving it is too big IMHO.

It's not a SAT solver (yet) and will have trouble to precisely handle arbitrarily large problems. So you have to lead it a bit, sometimes.

Post reply on HN