AlphaEvolve isn't an LLM - it's an evolutionary coding agent that uses an LLM fo...

AlphaEvolve isn't an LLM - it's an evolutionary coding agent that uses an LLM for code generation.

This is part of Google/DeepMind's "Alpha" branding (AlphaGo, AlphaZero, AlphaFold) of bespoke machine learning solutions to tough problems.

It sounds like AlphaEvolve might do well on Chollet's ARC-AGI test, where this sort of program synthesis seems to be the most successful approach.

I find Tao's use of "extremize" vs "maximize" a bit jarring - maybe this is a more normal term in mathematics?