Re:AlphaEvolve: Gemini-powered coding agent scaling impact a...
by brkn on Thursday May 07, 2026 @12:23PM
(#48051296)
I would be interested to see how exactly the agent helped. How was it used, where did it lead to the given improvement and in how far would it have taken a human to come to the same solution.
[ Parent
| on HN ]
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a...
by armanj on Thursday May 07, 2026 @03:21PM
(#48053628)
seems like `karpathy/autoresearch` on steroids
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a...
by j2kun on Thursday May 07, 2026 @12:48PM
(#48051635)
The blog post has many links to papers and preprints discussing this exact question.
Re:AlphaEvolve: Gemini-powered coding agent scaling impact a...
by Lt_Riza_Hawkeye on Thursday May 07, 2026 @02:45PM
(#48053192)
The CANOS arxiv link says absolutely nothing about AlphaEvolve, Gemini, or LLMs. It seems to use purely traditional ML models. If AE did in fact write a quick script to test different configurations in order to optimize the results, they don't seem to have bothered to write about it.
I can't read the Nature paper about DeepConsensus, but from the summary, it doesn't really explain what role AE had in improving DC. It would be nice to be able to read about what role it actually played, and whether it used traditional or novel methods of performing it