# OpenAI's GPT-5.6 Sol autonomously post-trained the smaller Luna model with a "fairly underspecified prompt"

> Source: <https://the-decoder.com/openais-gpt-5-6-sol-autonomously-post-trained-the-smaller-luna-model-with-a-fairly-underspecified-prompt/>
> Published: 2026-07-10 18:43:47+00:00

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"](https://the-decoder.com/openais-gpt-5-6-sol-autonomously-post-trained-the-smaller-luna-model-with-a-fairly-underspecified-prompt/) appeared first on [The Decoder](https://the-decoder.com).