Notes

On papers, ideas, and things I'm thinking about.

Evidence on AI R&D Progress from NanoGPT

1 min metr.org

How much are AI agents accelerating AI R&D, and how is that changing over time? The NanoGPT speedrun leaderboard is one source of evidence: a public, cumulative record of pretraining optimizations contributed by humans and, recently, by agents.

AI R&D evals

On the Subtleties of Software Optimization Evals

3 min

Small metric choices in software optimization benchmarks can create brittle aggregates and misleading capability conclusions. A look at how harmonic mean aggregation and correctness penalties interact in optimization evals.

benchmarks evals software optimization

Building Blocks to AI Timelines

6 min

Notes and intuitions on economic growth models, functional forms, and how they connect to forecasting AI progress. Part of a series on economics basics for AI forecasting.

economics AI progress forecasting growth models functional forms