AISC project: How promising is automating alignment research? (literature review)

Bogdan Ionut Cirstea28 Nov 2023 14:47 UTC

4 points

1 comment1 min readLW link

AI-Assisted Alignment AI Safety Camp Literature Reviews AI

Apply to work on this project with me at AI Safety Camp 2024 before 1st December 2023.

What links here?

Paper review: “The Unreasonable Effectiveness of Easy Training Data for Hard Tasks” by Vassil Tashev (29 Feb 2024 18:44 UTC; 11 points)

Bogdan Ionut Cirstea28 Nov 2023 14:47 UTC

4 points

1 comment1 min readLW link

AI-Assisted Alignment AI Safety Camp Literature Reviews AI

Ben Pace 28 Nov 2023 18:37 UTC
3 points
0
I would encourage you to include ~any of your content in the body of the LW post, as I expect ~most people do not click through to read links, especially with very little idea of what’s in the link.