OpenAI's GPT-5.6 Sol autonomously post-trained the smaller Luna model with a "fairly underspecified prompt"
🔒
https://the-decoder.com
«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 ...»
Automatische Weiterleitung...
1.5s