Long-time lurker, first-time poster. After parting ways with my last professional role, I’ve decided to get more involved in AI Safety. I’ve proposed what I think is a novel step towards corrigibility. The very short overview is at: https://danparshall.com/papers/navigator_core_blog.pdf
Hi folks,
Long-time lurker, first-time poster. After parting ways with my last professional role, I’ve decided to get more involved in AI Safety. I’ve proposed what I think is a novel step towards corrigibility. The very short overview is at:
https://danparshall.com/papers/navigator_core_blog.pdf
The more developed version is at:
http://danparshall.com/papers/navigator_core.pdf
I welcome feedback, either here or via email.