Naval Amplifies DeepSeek Explainer: SFT Is a Bike Manual, RL Is Learning to Ride
McDonaghMatthew · x · 2026-09-06
Naval quoted Matthew McDonagh's ELI5 explainer on DeepSeek: "Imagine teaching a child to ride a bike. You could give them a detailed manual (Supervised Fine Tuning), but they'll likely learn better by trying it themselves (Reinforcement Learning), falling, getting up, and gradually improving." McDonagh celebrated being quoted, urging everyone to keep writing words and analogies that make hard technical concepts click.
Related event: Naval Uses Bike-Riding Analogy to Explain SFT vs RL(2 posts)→
More from Models
- Anthropic's Terra returns with better writing and 2X usage vs 6.1 Sol — weswinder · 2026-10-27
- User catches model failing to parse 400-paper file, citing stale news sources instead — jungofthewon · 2026-10-27
- Odd eval result: Gemini 4.1 Flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Poster surprised that v4.1 flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Dev claims Anthropic is baking 'sabotage' into model behavior for 'wrong' engineering — cephaloform · 2026-10-27
- Gemini fails at listing unread emails, tells user to search Gmail manually — gethackteam · 2026-10-27