Updates on AI Safety Research

Every AI story we track on AI Safety Research: 6 stories so far, each summarized in our own words and linked to the publisher that reported it.

Pulled from 125 sources

Today's stories

Machine Learning1 min read

CRUCIBLE: IARPA-Funded AI Alignment Research — Applications Open

LessWrongNov 3

This month

Society & Culture1 min read

AI speeds up 3rd party safety researchers by ~1.6x (via self-reports)

LessWrongOct 27

Public Sector1 min read

Setting the Scene (Public v1; October 25)

Alignment ForumOct 25

Society & Culture1 min read

The Alignment Journal: Our Approach and Related Projects

LessWrongOct 22

Public Sector1 min read

Launching the Hong Kong AI Safety Hub (HASH), a new home for AI safety work in Hong Kong

LessWrongOct 13

Agents1 min read

Agents let AI safety share experiments hourly, not just papers monthly

LessWrongSep 17

That's everything we have on AI Safety Research right now