Mollick's lab releases Primer: an agent that turns teacher lessons into playable simulations
emollick · x · 2026-11-13
Ethan Mollick's Generative AI Lab released Primer, an agent-driven system where a teacher talks through a lesson and gets back a playable, pedagogy-grounded simulation for students. The paper, prompts, and code are open; the system is model-neutral and was built with teacher input. The final appendix contains a prompt that hands the paper itself to an AI agent and tells it to build its own version of Primer — "a paper you can run."
More from coding & agent
- lclip CLI turns Liveclip tables into a Redis-style key-value store with a built-in web admin — firasd · 2026-11-13
- Founder vibe-codes a Calendly clone and shares the result — kylegawley · 2026-11-13
- HeyGen shares its MCP prompts for free, again — HeyGen · 2026-11-13
- Orchestrator rolls out to Pro subs, pairing Hydrogen and Argon to save quota — clmt · 2026-11-13
- Burkov: vibe coding turned failed projects from 'can't start' into 'so close to done' — burkov · 2026-11-13
- KubeCon demo scales agent swarm from 50 to 16 million actors in three days — rakyll · 2026-11-13