Andrew Trask: Pre/Post Training Should Just Be Called Training
iamtrask · x · 2026-11-12
Deep learning researcher Andrew Trask argues that the pre-training/post-training distinction has lost its meaning and the field should simply call both "training" — implying the boundary is blurring as RL-based post-training dominates frontier model development.
More from AGI Musings
- Steve Yegge runs a 50-agent software factory for $10k/month, shipping 50-100 features a day — TheTuringPost · 2026-11-12
- Diamandis: best diagnostician of 2030 will be a panel of arguing AI agents — PeterDiamandis · 2026-11-12
- Eric Elliott on going from $500K in tech to homeless, and an AI-era small-business outlook event — ericelliott_ · 2026-11-12
- Palantir CTO Slams Effective Altruism as Masad Questions Timing of Huang Controversy — BrettKrieger12 · 2026-11-12
- Can LLMs be trained to commit heresy? Post-training against conformity, rewarding truth by outcomes — dioscuri · 2026-11-12
- Spencer Greenberg Asks: Would You Speak to an Audience You Strongly Disagree With? — SpencrGreenberg · 2026-11-12