
2 - Learning Human Biases with Rohin Shah
AXRP - the AI X-risk Research Podcast
00:00
Is There a Reasonable or a Simple Planning Module?
In the paper, you sort of have these assumptions, one, two, a and two b, right? Which which he talked about a little bit. But im, i was wondering if hou could like more. Sir am ye i guess let's talk about those. Ye, a, so the first assumption, assumption, one which was needed across n both of these two situations i talk about is that the planning module is the same in scarecos for similar enough environments.
Transcript
Play full episode