OpenAI Says GPT-5.6 Sol Can Autonomously Post-Train
The Decoder · rss · 2026-07-11
The Decoder reports that OpenAI's GPT-5.6 Sol can autonomously post-train a smaller Luna model on a 'fairly vague' prompt.
The report also notes:
- On OpenAI's internal Recursive Self-Improvement (RSI) benchmark, Sol scored 16.2 points higher than GPT-5.5.
- OpenAI believes an 'automated researcher' is becoming achievable.
This is news about model self-improvement capabilities and internal evaluation progress.
More from Models
- Google says its most ambitious pre-training run yet has started for Gemini 4 — andrew_n_carr · 2026-07-22
- Sam Altman is headed to Washington to brief Congress on OpenAI’s GPT-6 line — inductionheads · 2026-07-22
- Benchmark chart pits GPT-5.6 Luna, Grok 4.5 and Gemini 3.6 Flash on price and scores — iruletheworldmo · 2026-07-22
- Claim says Kimi was distilled from Fable, sparking a model-attribution jab — cephaloform · 2026-07-22
- Gemini 3.6 Flash is now available in Antigravity and chat — MartianOnJupiter · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22