In this video, we review OpenAI’s recent blog post and announcement about super alignment, where they talk about their future plans to control AGI. We look at the state of the alignment problem today, and where it needs to be for us to protect the human race from extinction.
Enjoy 🙂
Follow me on Twitter ? – https://twitter.com/matthewberman
Subscribe to my Substack ?? – https://matthewberman.substack.com
Become a Patron ? – https://patreon.com/MatthewBerman
Join the Discord ? – https://discord.gg/xxysSXBxFW
Links:
Superalignment – https://openai.com/blog/introducing-superalignment
Previous Blog Post – https://openai.com/blog/our-approach-to-alignment-research
Red Teaming – https://www.deepmind.com/blog/red-teaming-language-models-with-language-models
