ferreirafabio/autoresearch-automl

Can LLMs beat classical HPO? A benchmark comparing classical, LLM-based, and hybrid methods on Karpathy's autoresearch.

4 best points · 2 comments · 1 Hacker News post · 61 GitHub stars · View on GitHub

Hacker News discussions

• LLMs Don't Quite Beat Classical Hyperparameter Optimization Algorithms (4 points, 2 comments, by achierius, 2026-05-01)