OpenAI is testing training LLMs to produce "confessions", or self-report how they carried out a task and own up to bad behavior, like appearing to lie or cheat (Will Douglas Heaven/MIT Technology Review)

Will Douglas Heaven / MIT Technology Review:
OpenAI is testing training LLMs to produce “confessions”, or self-report how they carried out a task and own up to bad behavior, like appearing to lie or cheat  —  OpenAI is testing another new way to expose the complicated processes at work inside large language models.

Posted from: this blog via Microsoft Power Automate.

Daily Deals