OpenAI researchers show that reinforcement learning on desired behavioral traits like truthfulness and corrigibility works across domains. Training on health data also improved deception detection, and the model scored better on 44 out of 53 benchmarks. The approach differs from Anthropic's constitution-based method.
The article OpenAI researchers show small doses of "beneficial trait" training make AI models broadly safer and harder to manipulate appeared first on The Decoder.
source & further reading
the-decoder.com — original article
Google appeals ruling that made it directly liable for AI-generated search overview content
Website "In the Weights" shows whether AI models know who you are
ChatGPT's new health upgrade beats doctor-written answers, OpenAI says