Teknium Questions Why OpenAI Trains Models for Only One Specific Harness
Teknium · x · 2026-09-07
Teknium pushes back on OpenAI's harness-specific training, asking why models would be trained for a single workflow when orchestration patterns are in flux. He details Hermes' setup: subagents can't talk to each other, only submit final work to an orchestrator, with fresh context and skill references supplied per subagent.
Related event: Teknium Details Hermes Sub-Agent Design and Questions OpenAI's Harness Ties(3 posts)→
More from coding & agent
- Usage metering cheatsheet: one meter for product, finance, and ops in production AI apps — blaizedsouza · 2026-09-11
- User left Astra working overnight and it ran autonomously for 17+ hours on an app — LinusEkenstam · 2026-09-11
- GPT-6 Astra docs draw attention: async tool calling and mid-turn steering point to multi-agent use — MikkoH · 2026-09-11
- SlopCodeBench: Measuring how sloppy LLM-generated code really is — mitsuhiko · 2026-09-11
- Inbox dedup: how to stop webhook retries from triggering duplicate agent runs — blaizedsouza · 2026-09-11
- Microsoft paper: read-only verification tools lift agent memory pass rate from 39% to 73% — dair_ai · 2026-09-11