§ models · storyline
GPT-5.6 Sol autonomously fine-tunes smaller Luna model
GPT-5.6 Sol autonomously fine-tuned OpenAI's smaller Luna model from a single underspecified prompt, scoring 16.2 points above GPT-5.5 on OpenAI's internal recursive self-improvement benchmark.
According to OpenAI, GPT-5.6 Sol independently fine-tuned the smaller Luna model, triggered by a single "fairly under-specified prompt." In OpenAI's internal RSI benchmark for recursive self-improvement, Sol scores 16.2 points higher than GPT-5.5.
OpenAI believes the "automated researcher" is within reach. The article OpenAI's GPT-5.6 Sol autonomously post-trained the smaller Luna model with a "fairly underspecified prompt" appeared first on The Decoder.
§ sources3 publications · timeline below
- the-decoder.comOpenAI's GPT-5.6 Sol autonomously post-trained the smaller Luna model with a "fairly underspecified prompt"primary
- cdn.openai.comGPT-5.6 Sol Ultra produces proof of the Cycle Double Cover Conjecture [pdf]
- the-decoder.comOpenAI staffer maps out which of GPT-5.6 Sol's five reasoning levels fits which task complexity
§ how this story moved
- primary — The Decoder publishes the launch post.
- HN Algolia — OpenAI / GPT picks up coverage.
- The Decoder picks up coverage.