michK/Autoresearch-for-Research

An LLM forms hypotheses, writes code, runs PDE simulations, and iterates — achieving 7–24× improvements across five physics domains on a single CPU VPS.

2 best points · 1 comments · 1 Hacker News post · 5 GitHub stars · View on GitHub

Hacker News discussions

• LLM autonomously runs physics research across 5 PDE systems (2 points, 1 comments, by mike_krugs, 2026-03-26)