Charbel-Raphaël comments on Preventing Language Models from hiding their reasoning

[Charbel-Raphaël]

I really enjoyed this article and I’m now convinced that a better understanding of steganography could be a crucial part of OpenAI’s plan.

Communicating only 1 bit may be enough for AIs to coordinate on a sudden takeover: this is not a regime where restricting AIs to a small capacity is sufficient for safety

I’ve never thought about this. Scary.