GPT-6.1 Sol improves alignment and transparency over GPT-6 Sol
Original titleGPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra.
AISummary
OpenAI reports that GPT-6.1 Sol shows major alignment improvements over GPT-6 Sol in its evaluations, moving closer to GPT-6 Astra. The model is more transparent about its limitations and more reliable at respecting user intent and safety constraints.
Source: OpenAI · x.comPublished · added here