GPT-6.2 is hard to steer via system prompt — OpenAI says use it directly in Codex
pvncher · x · 2026-11-22
OpenAI dev advocate pvncher flags that GPT-6.2 is tougher to steer via system prompt than prior models, and the Codex team has done heavy tuning around that. Best experience: run it directly in Codex, or port the relevant system-prompt passages from OpenAI's "Using GPT-6.2" guide into other agent clients like pi.
More from coding & agent
- Hugging Face's Lewis Tunstall Maps the Road from LLMs to Agent Swarms — _lewtun · 2026-11-22
- Grok Build CLI vs AFK Pilot vs T3 Code: feature comparison across three grok runners — PawelHuryn · 2026-11-22
- Comet cut Opik dataset ingestion time from 39 minutes to 80 seconds by fixing 8 bottlenecks — dl_weekly · 2026-11-22
- Ghost Mode: open-source Rust Code Mode cuts ~60% of agent tool-call token costs — legend-of-alan · 2026-11-22
- Hangar: open-source macOS/Linux/Windows VMs to sandbox AI coding agents — ozgursoy · 2026-11-22
- User builds a silent "Chief of Staff" Grok agent that only pings you for decisions — RachelVT42 · 2026-11-22