Future of AI. AI alignment problem. Mikhail Samin
Feb 24 2023
43 mins
Today’s guest of my podcast is Mikhail Samin, AI safety researcher, effective altruist, creator of AudD, ex-head of Russian pastafarian church. In this episode we are discussing the problem of AI alignment (unfriendly AI), ChatGPT, and AI safety.
Links to explore:
https://www.agisafetyfundamentals.com/
https://www.youtube.com/channel/UCLB7AzTwc6VFZrBsO2ucBMg
https://aisafety.inf