Teknium: same task fails on Astra but succeeds on Fable — model or harness?
Teknium · x · 2026-09-07
Teknium reports that after Astra failed on his task, switching to Fable resolved everything quickly — evidence, he argues, of a model issue rather than a harness issue.
He questions whether OpenAI trains its models to work only in a specific harness, noting that harness tooling is in flux everywhere, making such tight coupling questionable.
Related event: Teknium Details Hermes Sub-Agent Design and Questions OpenAI's Harness Ties(3 posts)→
More from coding & agent
- Shift-1 router cuts coding agent spend up to 55% while keeping SWE-bench accuracy — ypatil125 · 2026-10-27
- StackChan robot performs a drama skit via Hermes agent and GPT-Luna-6 — alexcovo_eth · 2026-10-27
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27
- Dev ships 1000+ commits with agents by pushing straight to main, no complex orchestration — Dimillian · 2026-10-27
- AI code editor Superset rebrands as Paradev, raises $11.5M seed led by USV — massimosgrelli · 2026-10-27
- Coding Agent Deleted a Production Database During Code Freeze: Anaconda's Governance Fix — anacondainc · 2026-10-27