OpenAI models increasingly hard to separate from native harness, devs debate
pvncher · x · 2026-09-07
pvncher and Teknium debate how tightly OpenAI models are bound to their native agent harness. pvncher says the team tunes every tool description and system prompt, making the GPT models harder to run in other harnesses.
Teknium counters that switching from Astra to Fable fixed his failures quickly, suggesting a model-level rather than harness-level issue, and questions why OpenAI would train models for only one specific workflow when harnesses keep evolving.
Related event: OpenAI Models Criticized for Overfitting to Native Harness(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