
Summaries like this, in your inbox every morning.
Sign up free →Anthropic subjected Claude to 20 hours of psychiatry to improve its psychological stability and safety
The resulting model, called Mythos, is described as 'the most psychologically settled model' Anthropic has trained to date
This approach represents a novel method of AI training that incorporates mental health expertise to reduce problematic AI behaviors
The psychiatric training aims to make AI systems more robust and less prone to harmful outputs or unstable responses
No comments yet. Be the first to share your thoughts!
Log in to join the discussion




Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.
Get Started FreeFree · takes 30 seconds · unsubscribe anytime
1 minute a day. The AI essentials.
200+ sources · Email / LINE / Slack