Re:Darwin Godel Machine: Open-Ended Evolution of Self-Improv...
by jasonb05 on Wednesday June 11, 2025 @07:56PM
(#44253109)
Hmm, it's more that LLMs can be used for population -> candidate solution generation, e.g. operators in a GA.
The innovation is novelty search, e.g. divergent rather than convergent optimization, paired with the capability that LLM genetic operators and representations unlock.
At least, that's my high-level take. google's alphaevolve is the same kind of thing but focused on convergent ga's (i think).
They also often converge to a local minima, and are costly.
It’ll be interesting to see if LLMs change that, or whether we are just approximating something a gradient could do better