x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
AI Safety — LessWrong
AI Safety
This page is a stub.
Subscribe
Discussion
1
Subscribe
Discussion
1
Posts tagged
AI Safety
Most Relevant
2
251
OpenAI: Astra covertly underperforms on safety research
Ω
Zach Stein-Perlman
14d
Ω
22
2
221
Our Most Aligned Model Yet
Edward James Young
8d
16
2
198
Near Horizons
David Africa
10d
26
2
162
For Love of the Lightcone, Don't Partisanize AI Safety
DanB
2mo
60
2
157
Where is all the AI safety research uplift?
Ω
Buck
9d
Ω
32
2
107
Announcing AIXI Labs
Cole Wyeth
,
Aram Ebtekar
,
michaelcohen
,
Matthias Dellago
,
Marcus Hutter
4mo
9
2
21
Open Problems in Mechanistic Intepretability of Biological AIs
Ihor Kendiukhov
3mo
0
2
20
Synthetic Scalable Oversight
Alexander Heckett
,
Shivansh Gour
,
Riyaz Ahuja
,
Tate Rowney
,
ishinshah
4mo
1
2
17
Setting the Scene (Public v1; October 2026)
Ω
Chris_Leong
24d
Ω
1
2
16
Notes on “We’re in Triage Mode for AI Safety” by Miles Brundage
Ω
Chris_Leong
22d
Ω
0
2
13
The Case for Physical AI Safety
kaylene_stocking
,
Bear Häon
4mo
2
2
11
Agents let AI safety share experiments hourly, not just papers monthly
Jason Fantl
2mo
0
2
10
Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment
Roland Pihlakas
,
lenz
,
Three Laws
4mo
0
2
6
We want to run AI safety events for you!
andrewxcai
,
Sefika
,
giantpandas
,
nathgn
5d
0
1
174
Existential AI safety needs an effective social movement. PauseAI is building it
Maxime Fournes
,
Matilda da Rui
5mo
56