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
- Vercel owns 48% of ChatGPT citations for deployment questions—here's how — jia_seed · 2026-09-08
- Solving agentic amnesia: a file-system state machine for Claude Code — SnooComics4579 · 2026-09-08
- Omagrid turns multiple Omarchy machines into an AI grid with three orchestration modes — dee_hw · 2026-09-08
- Stanford releases free full course on self-improving AI agents — Saboo_Shubham_ · 2026-09-08
- Open-sourced clay-style 3D kids game built with Claude, method fully documented — dotey · 2026-09-08
- Steve Yegge: Fable 5.1 rewrote 30% of Wheelhouse factory after Fable 5 trainwreck — Steve_Yegge · 2026-09-08