Hacker News: hariseldom

New comment by hariseldom in "A Theory of Deep Learning"

hariseldom — Wed, 06 May 2026 20:44:36 +0000

These are the same complaints I had. Also felt like it was high quality ai writing, possibly because of the style choices like "Benign overfitting is noise sitting in the reservoir at interpolation. XYZ is ..." and because of the similarity it has to the times I ended up with chatgpt or gemini creating very detailed and plausible reports about my own crackpot or vague-enough-to-be-useless ideas.

New comment by hariseldom in "Stop Flock"

hariseldom — Wed, 15 Apr 2026 10:36:35 +0000

a missed opportunity, going with StopFlock instead of FlockOff dot com

New comment by hariseldom in "AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms"

hariseldom — Thu, 15 May 2025 19:35:22 +0000

https://arxiv.org/pdf/2501.09891v1 from deepmind in January goes into the evolutionary algorithm a bit - no math though.