OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.
OpenAI 官方新闻 · Source excerpt
OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.
This is a feed excerpt. Read the original source for the full report. Editorial review is pending.
Original sourceOpenAI 官方新闻Capabilities are described by the vendor and have not been independently tested.
Tools in this article
Our framework for reporting model misalignment · AI NEWS
