Nat Lambert: post-training and post-post-training are really different arts
natolambert · x · 2026-11-05
Nat Lambert, former HF post-training lead, argues in a terse post that post-training and post-post-training are fundamentally different disciplines — a nod to the emerging split between classic RLHF-style tuning and environment/experience-driven improvement methods.
More from Models
- 11,398 real-world evals: GPT-6 Astra stands out in 5-VLA policy comparison — DJiafei · 2026-11-05
- Researcher disqualifies Olmo 3 evals for cherry-picking comparisons, dodging Qwen baselines — JJitsev · 2026-11-05
- Sentry founder: $25/day quota can't even complete a reasonable session — zeeg · 2026-11-05
- ScreamingFace launches leaderboards showing multi-model systems can beat the best single model inside them — iamtrask · 2026-11-05
- OpenMined launches ScreamingFace: open-source model fusions beat best single models on live leaderboards — iamtrask · 2026-11-05
- DeepSeek 4.1 Flash impresses dev: 641M tokens cost just $4 — jasonkneen · 2026-11-05