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

Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

twitter.com

Post reply on HN
Print view View original

71–80 of 208 posts

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#71

Post by bitwize »

madrox wrote: post #66
vatsachak wrote: post #36

I've always said this but AI will win a fields medal before being able to manage a McDonald's. Math seems difficult to us because it's like using a hammer (the brain) to twist in a screw (math). LLMs are discovering a lot of new math because they are great at low depth high breadth situations. I predict that in the future people will ditch LLMs in favor of AlphaGo style RL done on Lean syntax trees. These should be a…

> I've always said this but AI will win a fields medal before being able to manage a McDonald's. I love this and have a corollary saying: the last job to be automated will be QA. This wave of technology has triggered more discussion about the types of knowledge work that exist than any other, and I think we will be sharper for it.

The ownership class will be sharper. They will know how to exploit capital and turn it into more capital with vastly increased efficiency. Everybody else will be hosed.

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#73

Post by bitwize »

vatsachak wrote: post #53
slopinthebag wrote: post #46

Earlier quoted context omitted.

> AI will win a fields medal before being able to manage a McDonald's Of course, because it takes multi-modal intelligence to manage a McDonalds. I.e. it requires human intelligence. > I predict that in the future people will ditch LLMs in favor of AlphaGo style RL Same for coding as well. LLM's might be the interface we use with other forms of AI though.

Something like building Linux is more akin to managing a McDonald's than it is to a 10 page technical proof in Algebraic Groups. Programming is more multimodal than math. Something like performance engineering might be free lunch though

But LLMs have proven themselves better at programming than most professional programmers.

Don't argue. If you think Hackernews is a representative sample of the field then you haven't been in the field long enough.

What LLMs have actually done is put the dream of software engineering within reach. Creativity is inimical to software engineering; the goal has long been to provide a universal set of reusable components which can then be adapted and integrated into any system. The hard part was always providing libraries of such components, and then integrating them. LLMs have largely solved these problems. Their training data contains vast amounts of solved programming problems, and they are able to adapt these in vector space to whatever the situation calls for.

We are already there. Software engineering as it was long envisioned is now possible. And if you're not doing it with LLMs, you're going to be left behind. Multimodal human-level thinking need only be undertaken at the highest levels: deciding what to build and maybe choosing the components to build it. LLMs will take care of the rest.

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#74

Post by cindyllm »

slopinthebag wrote: post #59
vatsachak wrote: post #53

Earlier quoted context omitted.

Something like building Linux is more akin to managing a McDonald's than it is to a 10 page technical proof in Algebraic Groups. Programming is more multimodal than math. Something like performance engineering might be free lunch though

Yeah, it's hard to compare management and programming but they're both multimodal in very different ways. But there's gonna be entire domains in which AI dominates much like stockfish, but stockfish isn't managing franchises and there is no reason to expect that anytime soon. I feel like something people miss when they talk about intelligence is that humans have incredible breadth. This is really what differentiates…

[dead]

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#75

Post by ChrisClark »

frizlab wrote: post #15
dataviz1000 wrote: post #5

Earlier quoted context omitted.

I got Claude to self reference and update its own instructions to solve making a typed proxy API of any website. After a week, scores of iterations, it can reverse engineer any website. The first few days I had to be deeply involved with each iteration loop. Domain knowledge is helpful. Each time I saw a problem I would ask Claude to update its instructions so it doesn't happen again. Then less and less. Eventually i…

> I would go for a 2 or 3 hour walk with my phone using the remote control feature looking every 5 - 10 minutes to make sure it doesn't need human help. That is a nightmarish scenario tbh

So sitting at a desk is nicer than a walk outside for you? Why would relaxation be a nightmare?

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#76

Post by dataviz1000 »

frizlab wrote: post #15
dataviz1000 wrote: post #5

Earlier quoted context omitted.

I got Claude to self reference and update its own instructions to solve making a typed proxy API of any website. After a week, scores of iterations, it can reverse engineer any website. The first few days I had to be deeply involved with each iteration loop. Domain knowledge is helpful. Each time I saw a problem I would ask Claude to update its instructions so it doesn't happen again. Then less and less. Eventually i…

> I would go for a 2 or 3 hour walk with my phone using the remote control feature looking every 5 - 10 minutes to make sure it doesn't need human help. That is a nightmarish scenario tbh

That nightmarish scenario is what T.S. Eliot was describing in "The Wasteland" which "portrays deep, existential ennui and boredom as defining symptoms of modern life following World War I."

Later this boredom was described by the Stones, "And though she’s not really ill / There’s a little yellow pill / She goes running for the shelter of a mother’s little helper".

It is a nightmare. Mostly what I'm thinking about while the agents are running is how bored I'm going to be. That is the joke, my deep thought on T.S. Eliot are about the wasteland this thing is going to create.

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#78

Post by dataviz1000 »

emp17344 wrote: post #70
ale wrote: post #37

Earlier quoted context omitted.

This type of slop comment is somehow worse than spam. >After a week, scores of iterations, it can reverse engineer any website Cool, let’s see the proof.

There is no proof, just a self-congratulatory word salad with dubious authenticity. It’s insane how insufferable this place is now.

Here is a description of the iteration loop. [0] I'm working on another draft that will be much more polished and have better explanations of the iteration loop.

> There is no proof, just a self-congratulatory word salad with dubious authenticity.

I worked 8 days straight on that and have been working non-stop on the second draft that is much cleaner and safer. I'm a human being. Please don't be mean. If humanity does come to end, it won't be because of AI, it will be because we can't stop being assholes to each other.

[0] https://github.com/adam-s/intercept/tree/main?tab=readme-ov-...

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#79

Post by abcde666777 »

bitwize wrote: post #73
vatsachak wrote: post #53

Earlier quoted context omitted.

Something like building Linux is more akin to managing a McDonald's than it is to a 10 page technical proof in Algebraic Groups. Programming is more multimodal than math. Something like performance engineering might be free lunch though

But LLMs have proven themselves better at programming than most professional programmers. Don't argue. If you think Hackernews is a representative sample of the field then you haven't been in the field long enough. What LLMs have actually done is put the dream of software engineering within reach. Creativity is inimical to software engineering; the goal has long been to provide a universal set of reusable components…

A bit optimistic I'd say. It's put some software engineering within reach of some people who couldn't do it prior. Where 'some' might be a lot, but still far from all.

I was thinking the other day of how things would go if some of my less tech savvy clients tried to vibe code the things I implement for them, and frankly I could only imagine hilarity ensuing. They wouldn't be able to steer it correctly at all and would inevitably get stuck.

Someone needs to experiment with that actually: putting the full set of agentic coding tools in the hands of grandma and recording the outcome.

Re: Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem

#80

Post by falcor84 »

siva7 wrote: post #48
falcor84 wrote: post #30

Earlier quoted context omitted.

Nightmarish?! In comparison to the average person's actual job? I'm pretty sure that many people out there would sign up for a battle royale for a chance at such a job.

Would they? I'd love to get in touch

My clients have been burned before. Once you set up the battle royale with a trusted third party validating that there'll be an assured good job at the end, I promise I'll have enough candidates for you to fill up the first 10 competitions.
Post reply on HN