IAPS: Mapping Technical Safety Research at AI Companies

post by Zach Stein-Perlman · 2024-10-24T20:30:41.159Z · LW · GW · 3 comments

This is a link post for https://www.iaps.ai/research/mapping-technical-safety-research-at-ai-companies

Contents

3 comments

3 comments

Comments sorted by top scores.

comment by Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-10-24T20:54:43.852Z · LW(p) · GW(p)

My main takeaway would be that this seems like quite strong evidence towards the view expressed in https://www.beren.io/2023-11-05-Open-source-AI-has-been-vital-for-alignment/, that most safety research doesn't come from the top labs.

Replies from: Zach Stein-Perlman
↑ comment by Zach Stein-Perlman · 2024-10-24T21:07:46.141Z · LW(p) · GW(p)

How does this paper suggest "that most safety research doesn't come from the top labs"?

Replies from: bogdan-ionut-cirstea
↑ comment by Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-10-24T21:28:33.995Z · LW(p) · GW(p)

Indirectly, because 90 papers seems like a tiny number, vs. what got published on arxiv during that same time interval. (Depending on how one counts) I wouldn't be surprised if there were > 90 papers from outside the labs even looking only at the unlearning category.