RT by @sama: Today we open sourced many of OpenAI's monitorability evaluations. We hope that the research community and other model developers can build upon th... (opens in new tab)
Today we open sourced many of OpenAI's monitorability evaluations. We hope that the research community and other model developers can build upon them and use them to evaluate the monitorability of their own models. alignment.openai.com/monitor…
Read the original article