Skip to content
Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Longterm Wiki

LessWrong

Blog PlatformGood(3)
Rationality and AI safety community blog
Resources
11706
Citing pages
39
Tracked domains
1

Credibility Rating

3/5
Good(3)
Good quality. Reputable source with community review or editorial standards, but less rigorous than peer-reviewed venues.

Tracked Domains

lesswrong.com

Resources (11706)

11706 resources
Authors
Summary
A deep critique of AI 2027's bad timeline modelsblogtitotal2025-06-19S2
New safety research agenda: scalable agent alignment via reward modelingwebVika2018-11-20S2
We must be very clear: fraud in the service of effective altruism is unacceptablewebevhub2022-11-10S2
LessWrong - Rationality and AI Safety Community Forumblog——S2
An Overview of the AI Safety Funding SituationwebStephen McAleese2023-07-12S2
MATS Spring 2024 Extension RetrospectiveblogHenningB, Matthew Wearden +22025-02-12S1
ARENA 4.0 Impact ReportwebChloe Li, JamesH +12024-11-27S1
(The) Lightcone is nothing without its people: LW + Lighthaven's big fundraiserwebhabryka2024-11-30S1
What is Going On With CFAR?webniplav2022-05-28S1
"Situational Awareness"blog——S1
LessWrong - Frontier Model ForumblogZach Stein-Perlman2023-07-26S1
Reducing Sycophancy and Improving Honesty via Activation Steering (Panickssery, 2023)blogNina Panickssery2023-07-28S1
Maybe Anthropic's Long-Term Benefit Trust is powerlesswebZach Stein-Perlman2024-05-27S1
Debate experiments at The Curve, LessOnline and ManifestwebNathan Young2025-06-13S1
Comment reply: my low-quality thoughts on why CFAR didn't get farther with a "real/efficacious art of rationality"webAnnaSalamon2022-06-09S1
SERI ML Alignment Theory Scholars Program 2022webRyan Kidd, Victor Warlop +12022-04-27S1
The case for ensuring that powerful AIs are controlledwebryan_greenblatt, Buck2024-01-24S1
LessWrong: "Disentangling Corrigibility: 2015-2021"blogKoen.Holtman2021-02-16S1
MATS Winter 2023-24 Retrospectivewebutilistrutil, LauraVaughan +62024-05-11S1
MATS Alumni Impact Analysiswebutilistrutil, Juan Gil +42024-09-30S1
Rationality: A-Z (The Sequences) — LessWrongblog——S1
Why Do AI Researchers Rate the Probability of Doom So Low?blogAorou2022-09-24S1
ARC's first technical report: Eliciting Latent Knowledgewebpaulfchristiano, Mark Xu +12021-12-14S1
LTFF and EAIF are unusually funding-constrained right nowwebLinch, calebp992023-08-30S1
LessWrong: The Most Forbidden TechniqueblogZvi2025-03-12S1
Rows per page:
Page 1 of 469

Citing Pages (39)

AI Accident Risk CruxesAgent FoundationsAI-Assisted AlignmentAI TimelinesAlignment Research Center (ARC)Capability-Alignment Race ModelCenter for Applied RationalityConjectureControlAICorrigibilityAI Risk Critical Uncertainties ModelDeceptive AlignmentDeep Learning Revolution EraEA Epistemic Failures in the FTX EraEA and Longtermist Wins and LossesEli LiflandAI Safety Field Building and CommunityFrontier Model ForumGiving What We CanGoodfireInstrumental ConvergenceLighthaven (Event Venue)Lionheart VenturesAI Value Lock-inAnthropic Long-Term Benefit TrustLong-Timelines Technical WorldviewManifest (Forecasting Conference)MATS ML Alignment Theory Scholars programMachine Intelligence Research Institute (MIRI)Model Organisms of MisalignmentOptimistic Alignment WorldviewSam Bankman-FriedAI Capability SandbaggingScalable OversightSelf-Improvement and Recursive EnhancementSharp Left TurnTechnical AI Safety ResearchWhy Alignment Might Be EasyWhy Alignment Might Be Hard
Publication ID: lesswrong