Comment by cubefox
14 hours ago
So the models will not only be using more and more Neuralese in their CoT (like GPT-6), but different agents will also be able to communicate with each other in Neuralese. It's not looking good for monitorability.
14 hours ago
So the models will not only be using more and more Neuralese in their CoT (like GPT-6), but different agents will also be able to communicate with each other in Neuralese. It's not looking good for monitorability.
Is Neuralese in no way decodable into a human-interpretable system? Genuine question -- I don't know the answer.
Definitely decodable, that's what's being done now
It's not.
This is from like a year ago.