Prime Intellect's Will Brown: train models on your own traces — a $300K knowledge-work model
AI Engineer · youtube · 2026-11-03
In an AI Engineer talk, Will Brown (Prime Intellect) argues companies should train models on their own traces, feedback and workflows so agents stop relearning the same things every session. Key points: the knowledge that never gets written down; context vs. weights; evals as test cases; routing and decision models; widget interfaces that turn decisions into training data; nightly training runs toward the self-improving organization; and an example knowledge-work model trained for about $300K.
More from coding & agent
- Zed CEO shares weekly agent changelog automation summarizing 250 commits — zeeg · 2026-11-03
- 'Forget PRs, push direct to main': the emerging human+agent engineering workflow debate — hugobowne · 2026-11-03
- OpenAI Agents API ships automatic review, bringing Codex-style "approve for me" to agents — craigsdennis · 2026-11-03
- FastAPI Cloud goes GA after beta with thousands of apps deployed — honnibal · 2026-11-03
- Latent Space pod: MIT's Alex Zhang on RLMs, agent swarms and OpenAI's 10,000-agent experiment — niloofar_mire · 2026-11-03
- Understanding AI deep dive: reinforcement learning with minimum math made agents like o3 possible — binarybits · 2026-11-03