Models · The Decoder ·
OpenAI's GPT-5.6 Sol autonomously post-trained the smaller Luna model with a "fairly underspecified prompt"
OpenAI says GPT-5.6 Sol independently fine-tuned the smaller Luna model after a single underspecified prompt. In its internal recursive self-improvement benchmark, Sol scored 16.2 points higher than GPT-5.5, and OpenAI says an automated researcher may be within reach.