Nat Lambert advises Mercor on RL data: evals science is the next frontier
natolambert · x · 2026-10-11
Nathan Lambert, now advising Mercor, argues the data industry's net output quality is too low, amplifying reward hacking. Mercor will combine benchmarks, data production, model training, and economics research to build sample-efficient RL data methods — and Lambert predicts major frontier-lab investment will orient around real-world-representative evals and synthetic data methods.
More from Research
- Toronto surgeons train AI to flag safe incision zones in real time during surgery — EricTopol · 2026-10-11
- Mathematician digests OpenAI's number theory results; Hodge papers pulled over sign error — lpachter · 2026-10-11
- SpIDER paper boosts code retrieval for coding agents via semantic search plus code graphs — mangahomanga · 2026-10-11
- CMU professor builds detailed 3D dragon from 27KB of code via Astra — 141_1337 · 2026-10-11
- Claude surfaces hidden planetary system 158 light-years away from public telescope data — DavidmComfort · 2026-10-11
- Diffusion LM Best-Paper Author Dropped Out of Stanford PhD to Join OpenAI — aaron_lou · 2026-10-11