OpenAI says GPT-6 Sol/Luna improve on GPT-5.6 in alignment evals via Astra advances
OpenAIDevs · x · 2026-09-23
OpenAI's dev account said GPT-6 Sol and Luna build on the Astra project's alignment advances, showing improvements over their GPT-5.6 counterparts in internal alignment evaluations. The post also recaps GPT-6's improved prompt caching: agents do less redundant processing and more context stays reusable across reasoning effort and tool configuration changes.
More from Models
- Gemini re-renders images as text when vision is removed, dropping only 6% WSR — zacharynado · 2026-11-12
- Google's Physical-Engineering's Last Exam: all 14 frontier models score below 50% — dl_weekly · 2026-11-12
- Commit leak reveals unreleased Gemini 4 variants: Argon, Hydrogen and Helix (unconfirmed) — BlackHC · 2026-11-11
- Rewiring just 89 of 442,368 neurons in Qwen3-8B matches full SFT for a persona — maxsloef · 2026-11-11
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-11
- Zvi: being forced back to an older model is the best reminder of AI progress — TheZvi · 2026-11-11