Bespoke Labs post-trains models on code repos with SFT plus GRPO
AlexGDimakis · x · 2026-09-04
New research from Bespoke Labs (with support from Thinking Machines / John Schulman): post-training a model to specialize on a given GitHub repository. Starting from the Inkling base, they run SFT on trajectories from a strong teacher model, then GRPO reinforcement learning on repo-specialized curated environments, substantially improving repo-specific performance.
More from coding & agent
- Developer builds himself a 'Rork MoTS' agent on Grok Bot, aiming for full autonomy before GTA 6 — rudrank · 2026-10-21
- OpenAI Live API tip: control voice sessions from your backend via sideband WebSocket — pbbakkum · 2026-10-21
- OpenAI's MultiLangBench: PHP scores highest (91.3%) at building a database engine from scratch — ricklamers · 2026-10-21
- UserProof lets Claude Code watch your user session recordings and boost conversion for $29/mo — doooyle · 2026-10-21
- dphnAI's distributed inference network served 32B DeepSeek tokens in 24h, ~6% of Venice's daily volume — Ronangmi · 2026-10-21
- Superconductor revamps agent picker spanning 8 coding agents with search and favorites — sergeykarayev · 2026-10-21