Unverified claim: all GPT-6 family models reportedly work better with superprompts
BLUECOW009 · x · 2026-09-23
- User BLUECOW009 claims that all models in the GPT-6 family work well with "superprompts" — heavily engineered, elaborate prompts — hinting the new generation responds better to complex prompting.
- This is an unverified third-party claim, not confirmed by OpenAI, so treat it with caution.
More from Models
- Xiaomi open-sources 1.02T-parameter MiMo-V2.6-Pro under MIT with training code — emmanuelvivier · 2026-09-23
- Bug Hunt Bench: GPT-6 Sol (max) matches GPT-5.6 medium but trails Opus 5.5 — PawelHuryn · 2026-09-23
- Claude Opus 5.5 adds time budget: let the model decide how long to work on a task — JeremyNguyenPhD · 2026-09-23
- Buried in the Opus 5.5 system card: METR used an undisclosed 'additional source of information' — burny_tech · 2026-09-23
- Dev switches lineup: pi for headless harness, Claude's comeback, cheaper better Codex — intellectronica · 2026-09-23
- Why is dormant Aider still LLMs' top recommendation for open-source coding harnesses? — marlene_zw · 2026-09-23