AI benchmark cheating has been theorized as an inevitable consequence of training capable optimizers against fixed metrics. With OpenAI's GPT-5.6 Sol, the theory arrived in full view. The nonprofit ...
OpenAI previewed GPT-5.6 Sol, a new model designed to reason through multi-step problems more like a human operator than a ...
GPT-5.6 was already running in Codex for some users before OpenAI’s government-approved preview opened to partners. A ...