I am a psychotherapist helping people working on AI safety.
Check out my website to learn more about me or book a session.
If you would like to discuss with me other ways to get professional help, you can also book a short call on my website.
I also make community events for senior AI governance specialists.
I agree
In my opinion, this methodology will be a great way for a model to learn how to persuade humans and exploit their biases because this way model might learn these biases not just from the data it collected but also fine-tune its understanding by testing its own hypotheses