x

LESSWRONG

LW

AI Safety — LessWrong

AI Safety

This page is a stub.

Add Posts

Posts tagged AI Safety

2

96Announcing AIXI Labs

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

1mo

9

2

20Synthetic Scalable Oversight

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

1mo

0

2

19Open Problems in Mechanistic Intepretability of Biological AIs

Ihor Kendiukhov

6d

0

2

11The Case for Physical AI Safety

kaylene_stocking, Bear Häon

1mo

2

2

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

Roland Pihlakas, lenz, Three Laws

1mo

0

1

164Existential AI safety needs an effective social movement. PauseAI is building it

Maxime Fournes, Espedair Street

2mo

54

1

122Synthetic Persona Pretraining: Alignment from Token Zero

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

3mo

27

1

78Door's Locked, Try the Window

Prakrat Agrawal, Jérémy Scheurer, Ariel_

2mo

0

1

77Research update: RL on Debate Games shows Proposal Accuracy uplift alongside Judge Hacking

lennie, joanv, Shi, Jacob Pfau

2mo

4

1

58Do LLMs Have Desires?

Christopher Ackerman

2mo

12

1

51Human-Guided Agentic Research: A Research Agenda

2mo

7

1

43Persona Cartography: Charting Language Model Personality Traits in Weight Space

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

1mo

0

1

39Don't normalize a permanent underclass (even a rich one)

1mo

7

1

39Help us launch AI safety university groups by referring potential founders

thomasrodskog, Jason Chin

1mo

1

1

37AI Safety Can't Afford a Second Cause

1mo

9

Load More (15/47)

Add Posts