MIT|Now we know what OpenAI’s superalignment team has been up to

 

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.

https://www.technologyreview.com/2023/12/14/1085344/openai-super-alignment-rogue-agi-gpt-4/