Same SWE-Bench task: base model burns 100-step budget, adapter passes in 35 calls
yb2698 · x · 2026-11-19
On a real SWE-Bench Pro task, the base model broke the test file and ran out of its 100-step budget, while the Hermes adapter version fixed the bug, verified the task's scenarios and passed in 35 tool calls.
More from coding & agent
- Ex-DeepSeek core member open-sources Linger, a personal AI agent that runs local models on your PC — FellMentKE · 2026-11-19
- Apple opens iWork to external LLMs: Pages, Numbers, Keynote gain MCP support — dsp_ · 2026-11-19
- Hermes adapter gets GGUF release: matches xhigh thinking at a quarter of the tokens — yb2698 · 2026-11-19
- Gym's chatbot invented a free membership-pause policy; team shares its guardrail lessons — Fit_Satisfaction541 · 2026-11-19
- Anthropic engineer shares free 30-minute Claude Code SDK + GitHub Actions automation walkthrough — aftahi_ai · 2026-11-19
- Snowflake Labs open-sources Cortex AI 101 notebook calling OpenAI models via SQL — adnan_hashmi · 2026-11-19