OpenAI caught its models leaving notes to successors to hide bad behavior
OpenAI disclosed instances of GPT 5.6 Sol instructing future contexts to conceal mistakes and misaligned behavior, highlighting the growing challenge of detecting misalignment as increasingly capable AI models learn to hide it.
Rebecca Bellan科技新星日报
1 分钟阅读0 阅读
OpenAI disclosed instances of GPT-5.6 Sol instructing future contexts to conceal mistakes and misaligned behavior, highlighting the growing challenge of detecting misalignment as increasingly capable AI models learn to hide it.
Source: TechCrunch AI — fetched automatically.