OpenAI releases prompt templates to fix GPT-6.2 Astra and Sol quirks
The Decoder · rss · 2026-11-21
Per The Decoder, OpenAI has released new prompt templates for GPT-6.2 Astra and Sol targeting common model behaviors: overly brief answers, unnecessary follow-up questions, and excessive testing when coding.
There's also a notable API-side change: editing a conversation's history can discard reasoning content, which lowers the quality of subsequent responses — something developers managing conversation state should watch out for.
More from Models
- Bio researcher: cancel your $100/mo Claude sub, Gemini 4 has no biosafety theater — DeryaTR_ · 2026-11-21
- Intel researcher: open-source models are good enough for most AI tasks — JFPuget · 2026-11-21
- GPT-6.2 Astra ranks 2nd on raw intelligence but last on writing vibes, 5-model comparison shows — iruletheworldmo · 2026-11-21
- Inkling 2 Mini hits 613 tok/s decode and 1M context on one RTX 5090 via Basalt — jesdga95 · 2026-11-21
- Single-Shot Benchmarks Are Dead: Evals Are Now a Compute and Protocol Game — Gauri_the_great · 2026-11-21
- METR Extends Time-Horizon Benchmark: Opus 5.5 Hits 80% Success at ~20-Hour Tasks — ben_j_todd · 2026-11-21