Same model, wildly different results: Fable 5.1 shines in Claude Code but stumbles elsewhere
altryne · x · 2026-09-21
altryne compares Fable 5.1 across coding agent harnesses and finds dramatic differences: in Claude Code the model documents requests in Linear, proactively offers to kick off jobs, and opens a PR in 22 seconds — while in other (unnamed) harnesses it behaves like "the slow kid." His takeaway: the harness around a model can matter as much as the model itself. He also laments running out of Fable tokens.
Related event: Hands-On: Fable 5.1 Crushes Astra in Coding Agent Tests(3 posts)→
More from coding & agent
- Google Rolls Out Browser Use to All Antigravity Users, Raising Doubts About Gemini Desktop App — testingcatalog · 2026-11-12
- OpenRouter launches Extractions API: typed JSON field extraction from text, images and PDFs — michellechen · 2026-11-12
- AgenticRL-Bench debuts: best agents pass only 14% of real-world agentic RL tasks — cuijiaxun · 2026-11-12
- SemiAnalysis: Persistent agents now eat 45% of our AI spend, and Perplexity's harness beats Claude Tags — dylan522p · 2026-11-12
- Gemini Agent Spans Workspace, Mobile, Desktop, and Slack via @-Mention — samcharrington · 2026-11-12
- Carbon + /swarm in Antigravity: Big Model Thinks, Lighter Models Work — samcharrington · 2026-11-12