🔮 Autoresearch and the experimental society

·Exponential View··

Science is the most reliable method humanity has found for producing knowledge. It has also, for most of history, been expensive to run. released 600 lines of Python code a few weeks ago that started to change that. His autoresearch (see EV#565) runs an autonomous experimental loop in which a human sets a strategic direction, defines what good looks like and the agent iterates towards success within the guardrails. In Andrej’s initial experiment, it trained a GPT-2-level model over two days, 11%...

Read full article →

Related Articles

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 18d ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 15d ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 18d ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 19d ago
ProgramBench: Can language models rebuild programs from scratch?
jonbaer · Hacker News · 14d ago