FrogNano: 4B model hits 61.5% on SWE-bench Verified with pure RL, zero distillation
sivareddyg · x · 2026-09-09
FrogNano is a Qwen3.5-4B model post-trained purely with RL on synthetic tasks from TaskPilot — no distillation, no teacher-trajectory SFT. Just 5 iterations × 300 tasks got it to 61.5% on SWE-bench Verified.
More from coding & agent
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26
- Fern 0.1 debuts: a model built to audit training data and debug agent traces for AI builders — bneyshabur · 2026-10-26
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Claude Code finds root backdoor in Honda Civic head unit, then debloats it — IndraVahan · 2026-10-26
- Claude Code + Monid MCP builds a $12K/year B2B prospecting engine on live data — aryanXmahajan · 2026-10-26
- Karpathy shares CLAUDE.md rulebook to stop AI coding agents from piling up tech debt — mdancho84 · 2026-10-26