Elicitation, the simplest way to understand post-training
interconnects.ai · 1,499 words · saved by 1 readers
An F1 analogy to help understand fast improvements in post-training on top of slow improvements in scaling.
Elicitation, the simplest way to understand post-training An F1 analogy to help understand fast improvements in post-training on top of slow improvements in scaling. Nathan Lambert Mar 10, 2025 48 9 Share Article voiceover 0:00 -8:25 Audio playback is not supported on your browser. Please upgrade. If you look at most of the models we've received from OpenAI, Anthropic, and Google in the last 18 months, you'll hear a lot of "Most of the improvements were in the post-training phase." The most recent one was Anthropic’s CEO Dario Amodei explaining Claude 3.7 on the Hard Fork Podcast : We are not
saved by
related reading
- On-Policy Distillation - Thinking Machines Labthinkingmachines.ai
- Scaling is subtler than it seemsberen.io
- Lil'Loglilianweng.github.io
- The Extreme Inefficiency of RL for Frontier Models - Toby Ordtobyord.com
- aiesi_post-training_public.pdfkawine.github.io
- Research Areas in Methods for Post-training and Elicitation (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
- Training Imperativesdan.io
- SFT, RL, and On-Policy Distillation Through a Distributional Lens | whnrehiew.github.io
- The least understood driver of AI progress | Epoch AIepoch.ai
- RL Scaling Laws for LLMs - by Cameron R. Wolfe, Ph.D.cameronrwolfe.substack.com
- Early Data Exposure Improves Robustness to Subsequent Fine-Tuningarxiv.org