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

A deep dive into self-improving AI and the Darwin-Gödel Machine

richardcsuwandi.github.io

Post reply on HN
Print view View original

91–100 of 103 posts

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#91

Post by drdeca »

mulmen wrote: post #85
auggierose wrote: post #81

Earlier quoted context omitted.

You don't make any sense. After all, your children are not your clones. You cannot "define" truth.

> After all, your children are not your clones. Human children are not clones but in asexual reproduction can produce literal clones. > You cannot "define" truth. I can and it isn't even hard. "Truth" is a word. It has a definition... by definition.

The word “word”, as usually used, is not a term which is defined to only apply to things which have definitions.

Generally one can describe how people use a word. (Though, see “semantic primes”; there has to be some cycles in what words are defined using what words.)

I think the quotations around “define” were intentional in the comment you replied to. I think their point wasn’t to say something like the “undefinability of truth” paradox (the whole “truth is in the metalanguage” thing), but to say that it seemed to them that you were kind of sneaking in assumptions as part of definitions, or something like that, idk.

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#92

Post by thom »

synctext wrote: post #36
thom wrote: post #30

Earlier quoted context omitted.

This is fairly close to how Eurisko worked tbh.

Eurisko is an expert system in LISP from 1983. right? In 2025 this formal logic is replace with stochastic LLM magic. interesting evolution.

What’s interesting to me is the rise of agentic approaches which are effectively “build a plethora of tools and heuristics” with an outer loop that combines, mutates and assigns values to these components. Where before that process was more rigid, we now have access to much more fluid intelligence but the structure feels similar - let the AI prod at the world and make experiments, then look at what worked and think of some plausible enhancements. At a certain point you’re enhancing the code that enhances the enhancer and all bets are off.

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#93

Post by thom »

TeMPOraL wrote: post #53
synctext wrote: post #36

Earlier quoted context omitted.

Eurisko is an expert system in LISP from 1983. right? In 2025 this formal logic is replace with stochastic LLM magic. interesting evolution.

Symbolic processing was obviously a bad approach to building a thinking machine. Well, obvious now, 40 years ago probably not as much, but there were strong hints back then, too. "AI agent" roughly just means invoking the system repeatedly in a while loop, and giving the system a degree of control when to stop the loop. That's not a particularly novel or breakthrough idea, so similarities are not surprising.

When “invoking” becomes “evolving” I think that remains very fertile ground.

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#94

Post by auggierose »

mulmen wrote: post #85
auggierose wrote: post #81

Earlier quoted context omitted.

You don't make any sense. After all, your children are not your clones. You cannot "define" truth.

> After all, your children are not your clones. Human children are not clones but in asexual reproduction can produce literal clones. > You cannot "define" truth. I can and it isn't even hard. "Truth" is a word. It has a definition... by definition.

Congrats. What did you achieve with your definition?

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#95

Post by thom »

TeMPOraL wrote: post #80
ryukafalz wrote: post #58

Earlier quoted context omitted.

I'm not convinced that symbolic processing doesn't still have a place in AI though. My feeling about language models is that, while they can be eerily good at solving problems, they're still not as capable of maintaining logical consistency as a symbolic program would be. Sure, we obviously weren't going to get to this point with only symbolic processing, but it doesn't have to be either/or. I think combining neural…

I agree that symbolic processing still has a role - but I think it's the same role it has for us: formal reasoning. I.e. a specialized tool. "Logical consistency" is exactly the kind of red herring that got us stuck with symbolic approach longer than it should. Humans aren't logically consistent either - except in some special situations, such as solving logic problems in school. Nothing in how we think, how we perce…

Yeah, I agree logic and symbolic reasoning have to be _applications_ of intelligence, not the actual substrate. My gut feel is that intelligence is almost definitionally chaotic and opaque. If one thing prevents superhuman AGI, I suspect it will be that targeted improvements in intelligence are almost impossible, and it will come down to the energy we can throw at the problem and the experiments we're able to run and evaluate.

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#96

Post by Xmd5a »

sgt101 wrote: post #79
Xmd5a wrote: post #78

Earlier quoted context omitted.

I guess this really depends on the problem but from the PromptWizard (PW) paper: | Approach | API calls | IO Tokens | Total tokens | Cost ($) | |----------|-----------|-----------|---------------|----------| | Instinct | 1730 | 67 | 115910 | 0.23 | | InsZero | 18600 | 80 | 1488000 | 2.9 | | PB | 5000 | 80 | 400000 | 0.8 | | EvoP | 69 | 362 | 24978 | 0.05 | | PW | 69 | 362 | 24978 | 0.05 | They ascribe this gain in ef…

Super interesting. I will have to read it - I will be looking to figure out if the tasks that they are working on significant/realistic? And are the improvements that they are finding robust?

The tasks these methods are tackling are generally significant and realistic. Think complex QA like HotPotQA or Google-Proof QA, math reasoning (GSM8K), coding challenges, and even agentic systems. It's not just about toy problems anymore.

Are the improvements robust? It's an evolving space, but the big win seems to be for smaller, open-source LLMs. These techniques can genuinely uplift them to near the performance of larger, proprietary models, which is massive for cost reduction and accessibility. For already SOTA models, the headline metric gains might be smaller single-digit percentages on very hard tasks, but this often translates into crucial improvements in reliability and the model's ability to follow complex instructions accurately.

"Textual gradient"-like mechanisms (or execution traces, or actual gradients over reasoning as in some newer work ) are becoming essential. Manually fine-tuning complex prompt workflows or prompts with many distinct nodes or components just doesn't scale. These automated methods provide a more principled and systematic approach to guide and refine LLM behavior.

So, less "spectacular" gains on the absolute hardest tasks with the biggest models, yes, but still valuable. More importantly, it's a powerful optimization route for making capable AI more efficient and accessible. And critically, it's shifting prompt design from a black art to a more transparent, traceable, and robust engineering discipline. That foundational aspect is probably the most significant contribution right now.

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#97

Post by nanfinitum »

I'm confused as to why they are using a tree model to describe the archive objects (the current model and newly minted child).

It seems to me that this is a linear process (parent -> mint new improved model -> evaluate model, if it passes -> mint new child -> make newly minted child the parent)

I feel like this makes a linked list model rather than a tree model. Am I wrong? What are the other nodes (outside of parent and child) supposed to be?

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#98

Post by kevinventullo »

mulmen wrote: post #66
auggierose wrote: post #19

Earlier quoted context omitted.

That is not true. There are plenty of ways not to reproduce and still to perpetuate your genetics. For example, if you don't have children of your own, but support people that have similar genetic traits to your own.

If they aren’t your children they aren’t your genes.

Not true. Nieces and nephews share ~25% of your genes.

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#99

Post by Grimblewald »

underlines wrote: post #59
kevinventullo wrote: post #9

“Gaming the system” means your metric is bad. In Darwinian evolution there is no distinction between gaming the system and developing adaptive traits.

In evolution there is no metric, that's a human made concept. In evolution the thing that kills you also evolves. The "metric" evolves.

there is an extremely clear and simple metric in evolution - number of copies of gene in subsequent iterations of the organism.

Re: A deep dive into self-improving AI and the Darwin-Gödel Machine

#100

Post by Grimblewald »

tonyhart7 wrote: post #31
auggierose wrote: post #19

Earlier quoted context omitted.

That is not true. There are plenty of ways not to reproduce and still to perpetuate your genetics. For example, if you don't have children of your own, but support people that have similar genetic traits to your own.

"but support people that have similar genetic traits to your own." but how its that works then??? does that mean your genetic trait is already there in the first place if its already there in the first place there must be something that start it now right, which basically counter your argument

If i support my brothers / sisters children, but have no children of my own, genetic data of mine survives into future generations, after all I share half my genetic data with my siblings.

If my helping these children gives them a competitive advantage in further reproduction, where the total reproductive strength of these well supported kids is greater than the total reproductive strength my family would have if I had my own children as well and split our resources, then this behaviour outcompetes simple reproduction, and if this behaviour is genetically encoded, becomes a dominant trait over time.

Post reply on HN