Now we know what OpenAI's superalignment team has been up to

The firm wants to prevent a superintelligence from going rogue. This is the first step.

ChatGPT Developer Predicts “SuperIntelligent” AI Will Arrive This

JETLAG RADIO 1042 BENKYO RADIO 1042 — zack.technology

Can Weak Models Control Strong Models? OpenAI Superalignment

OpenAI's Latest Goal: Prevent 'Superintelligent' AI From Killing

Scott Macon on LinkedIn: Wikipedia's Moment of Truth

OpenAI Launches Superalignment Taskforce — LessWrong

OpenAI's Superalignment Team: A Mission to Control

How ChatGPT Fractured OpenAI - The Atlantic

Larry Summers Is OpenAI's Surprise Pick to Mend Fences - WSJ