x

LESSWRONG

LW

AI Safety — LessWrong

AI Safety

This page is a stub.

Add Posts

Posts tagged AI Safety

2

168For Love of the Lightcone, Don't Partisanize AI Safety

17d

59

2

102Announcing AIXI Labs

Cole Wyeth, Aram Ebtekar, michaelcohen, Matthias Dellago, Marcus Hutter

2mo

9

2

21Open Problems in Mechanistic Intepretability of Biological AIs

Ihor Kendiukhov

2mo

0

2

20Synthetic Scalable Oversight

Alexander Heckett, Shivansh Gour, Riyaz Ahuja, Tate Rowney, ishinshah

3mo

1

2

13The Case for Physical AI Safety

kaylene_stocking, Bear Häon

2mo

2

2

10Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment

Roland Pihlakas, lenz, Three Laws

3mo

0

2

8Agents let AI safety share experiments hourly, not just papers monthly

17d

0

1

170Existential AI safety needs an effective social movement. PauseAI is building it

Maxime Fournes, Matilda da Rui

3mo

56

1

131Synthetic Persona Pretraining: Alignment from Token Zero

Julian Minder, Raghav Singhal, Viktor Moskvoretskii, Stefan Krsteski, ashtonanderson, rolandaydin, Robert West

4mo

27

1

78Door's Locked, Try the Window

Prakrat Agrawal, Jérémy Scheurer, Ariel_

3mo

0

1

78Research update: RL on Debate Games shows Proposal Accuracy uplift alongside Judge Hacking

lennie, joanv, Shi, Jacob Pfau

3mo

4

1

62Do LLMs Have Desires?

Christopher Ackerman

3mo

12

1

51Human-Guided Agentic Research: A Research Agenda

3mo

7

1

44Persona Cartography: Charting Language Model Personality Traits in Weight Space

antonghawthorne, Mariia Koroliuk, Irakli Shalibashvili, sidbaines, Clément Dumas, Konstantinos Voudouris, David Africa

3mo

0

1

40Announcing Lateral Workshop for experienced professionals moving into AI safety

Seth Lifland, Jacob Brinton, Topaz

2mo

1

Load More (15/58)

Add Posts