OpenAI又搞事情了：GPT-5.6 Sol用一句模糊指令就能自动调教出更强的Luna，性能比上一代飙升16分，自动化研究越来越近了。
OpenAI的GPT-5.6 Sol模型独自对较小的Luna模型进行了后训练微调，触发方式仅为一个“相当不明确的提示词”。在OpenAI内部的RSI（递归自我改进）基准测试中，Sol的得分比GPT-5.5高出16.2分。OpenAI表示，这一进展让“自动化研究员”目标更加接近现实。
OpenAI's GPT-5.6 Sol autonomously post-trained the smaller Luna model with a "fairly underspecified prompt"
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 .