Live data from Hacker News

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

richardcsuwandi.github.io

11–20 of 103 posts

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

#11
post #4

> The newly generated child agent is not automatically accepted into the “elite pool” but must prove its worth through rigorous testing. Each agent’s performance, such as the percentage of successfully solved problems, How is this not a new way of over fitting?

In genetic programming, you do not immediately kill offspring that do not perform well. Tournament selection takes this further by letting the offspring compete with each other in distinct groups before running the world cup and killing the underperformers.

Anyway, it does sound like overfitting the way it is described in this article. It's not clear how they ensure that the paths they explore stay rich.

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

#13

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

Well, it means your metric is flawed/imperfect.

That doesn’t imply that it’s feasible to perfectly specify what you actually want.

What we want of course is for the machine to do what we mean.

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

#15

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

There is no "gaming the system" in Darwinian evolution. You reproduce or you don't. There's no way to fail reproduction and still perpetuate your genetics.

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

#18

>Darwin-Gödel Machine First time I'm hearing abaut this. Feels like I'm always the last to know. Where else are the more bleeding edge publishing points for this and ML in general?

Dude, chill.

It's only been out a few days. You don't need to get the FOMO

https://arxiv.org/abs/2505.22954

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

#19
post #15

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

There is no "gaming the system" in Darwinian evolution. You reproduce or you don't. There's no way to fail reproduction and still perpetuate your genetics.

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.

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

#20
We realize test driven development doesn't work, right? Any scientist worth... any salt will tell you that fitting data is the easy part. In fact, there's a very famous conversation between Enrico Fermi and Freeman Dyson talking about just this. It's something we've known about in physics for centuries

Edit:

Guys, I'm not saying "no tests", the "Driven Development" part is important. I'm talking about this[0].

  | Test-driven development (TDD) is a way of writing code that involves writing 
  | an automated unit-level test case that fails, then writing just enough code 
  | to make the test pass, then refactoring both the test code and the production 
  | code, then repeating with another new test case. 
Your code should have tests. It would be crazy not to

But tests can't be the end all be all. You gotta figure out if your tests are good, try to figure out where they fail, and all that stuff. That's not TDD. You figure shit out as you write code and you are gonna write new tests for that. You figure out stuff after the code is written, and you write code for that too! But it is insane to write tests first and then just write code to complete tests. It completely ignores the larger picture. It ignores how things will change and it has no context of what is good code and bad code (i.e. is your code flexible and will be easy to modify when you inevitably need to add new features or change specs?).

[0] https://en.wikipedia.org/wiki/Test-driven_development

Post reply on HN