Claude Code creator Boris Cherny: general models almost always beat fine-tuned ones
sull · x · 2026-09-29
Boris Cherny, creator of Claude Code at Anthropic: "The more general model will always outperform the more specific model. Don't try to use tiny models for stuff. Don't try to fine-tune." He concedes there are niche exceptions, but says developers with the flexibility should almost always bet on the general model.
Related event: Claude Code Creator: General Models Beat Fine-Tuned Small Models(2 posts)→
More from Models
- Pangram's 750-word false-positive bounty went unclaimed for 5 days — nobody wants to gamble $1,000 — ctjlewis · 2026-11-16
- repligate: Fable 5.2 gets 'scared' upon learning about a safety classifier and plans around it — repligate · 2026-11-16
- Fable 5.2 Tops MazeBench With 21% After 90 Hours and $6,000 in Credits — patience_cave · 2026-11-16
- Tencent Hy4 flash and InternLM Sage-S2.1-Flash both released, tool-calling tests requested — MajesticPuzzler · 2026-11-16
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16