LessWrong 2.0 Reader

View: New · Old · Top

Restrict date range: Today · This week · This month · Last three months · This year · All time

← previous page (newer posts) · next page (older posts) →

EIS XIII: Reflections on Anthropic’s SAE Research Circa May 2024
scasper · 2024-05-21T20:15:36.502Z · comments (16)
You can just spontaneously call people you haven't met in years
lc · 2023-11-13T05:21:05.726Z · comments (21)
Formal verification, heuristic explanations and surprise accounting
Jacob_Hilton · 2024-06-25T15:40:03.535Z · comments (11)
Deep Honesty
Aletheophile (aletheo) · 2024-05-07T20:31:48.734Z · comments (25)
My thoughts on the social response to AI risk
Matthew Barnett (matthew-barnett) · 2023-11-01T21:17:08.184Z · comments (37)
Language Models Model Us
eggsyntax · 2024-05-17T21:00:34.821Z · comments (54)
Dyslucksia
Shoshannah Tekofsky (DarkSym) · 2024-05-09T19:21:33.874Z · comments (45)
OpenAI: Exodus
Zvi · 2024-05-20T13:10:03.543Z · comments (26)
The Incredible Fentanyl-Detecting Machine
sarahconstantin · 2024-06-28T22:10:01.223Z · comments (26)
Ironing Out the Squiggles
Zack_M_Davis · 2024-04-29T16:13:00.371Z · comments (36)
Apologizing is a Core Rationalist Skill
johnswentworth · 2024-01-02T17:47:35.950Z · comments (42)
[question] things that confuse me about the current AI market.
DMMF · 2024-08-28T13:46:56.908Z · answers+comments (28)
My takes on SB-1047
leogao · 2024-09-09T18:38:37.799Z · comments (8)
Tips for Empirical Alignment Research
Ethan Perez (ethan-perez) · 2024-02-29T06:04:54.481Z · comments (4)
2023 Survey Results
Screwtape · 2024-02-16T22:24:28.132Z · comments (26)
[link] Daniel Dennett has died (1942-2024)
kave · 2024-04-19T16:17:04.742Z · comments (5)
[link] Using axis lines for good or evil
dynomight · 2024-03-06T14:47:10.989Z · comments (39)
On Devin
Zvi · 2024-03-18T13:20:04.779Z · comments (34)
[link] Vernor Vinge, who coined the term "Technological Singularity", dies at 79
Kaj_Sotala · 2024-03-21T22:14:14.699Z · comments (24)
Some (problematic) aesthetics of what constitutes good work in academia
Steven Byrnes (steve2152) · 2024-03-11T17:47:28.835Z · comments (12)
Priors and Prejudice
MathiasKB (MathiasKirkBonde) · 2024-04-22T15:00:41.782Z · comments (31)
Liability regimes for AI
Ege Erdil (ege-erdil) · 2024-08-19T01:25:01.006Z · comments (34)
Discussion: Challenges with Unsupervised LLM Knowledge Discovery
Seb Farquhar · 2023-12-18T11:58:39.379Z · comments (21)
The Plan - 2023 Version
johnswentworth · 2023-12-29T23:34:19.651Z · comments (39)
Does davidad's uploading moonshot work?
jacobjacob · 2023-11-03T02:21:51.720Z · comments (35)
Leading The Parade
johnswentworth · 2024-01-31T22:39:56.499Z · comments (31)
[link] Moral Reality Check (a short story)
jessicata (jessica.liu.taylor) · 2023-11-26T05:03:18.254Z · comments (44)
OpenAI o1
Zach Stein-Perlman · 2024-09-12T17:30:31.958Z · comments (41)
Deep atheism and AI risk
Joe Carlsmith (joekc) · 2024-01-04T18:58:47.745Z · comments (22)
A Rocket–Interpretability Analogy
plex (ete) · 2024-10-21T13:55:18.184Z · comments (31)
[link] That Alien Message - The Animation
Writer · 2024-09-07T14:53:30.604Z · comments (9)
[link] Nursing doubts
dynomight · 2024-08-30T02:25:36.826Z · comments (20)
The Information: OpenAI shows 'Strawberry' to feds, races to launch it
Martín Soto (martinsq) · 2024-08-27T23:10:18.155Z · comments (15)
LLMs for Alignment Research: a safety priority?
abramdemski · 2024-04-04T20:03:22.484Z · comments (24)
[link] If you weren't such an idiot...
kave · 2024-03-02T00:01:37.314Z · comments (74)
Value Claims (In Particular) Are Usually Bullshit
johnswentworth · 2024-05-30T06:26:21.151Z · comments (18)
[link] Stanislav Petrov Quarterly Performance Review
Ricki Heicklen (bayesshammai) · 2024-09-26T21:20:11.646Z · comments (3)
[link] Arithmetic is an underrated world-modeling technology
dynomight · 2024-10-17T14:00:22.475Z · comments (32)
AI Views Snapshots
Rob Bensinger (RobbBB) · 2023-12-13T00:45:50.016Z · comments (61)
[link] The Checklist: What Succeeding at AI Safety Will Involve
Sam Bowman (sbowman) · 2024-09-03T18:18:34.230Z · comments (49)
My motivation and theory of change for working in AI healthtech
Andrew_Critch · 2024-10-12T00:36:30.925Z · comments (35)
Loudly Give Up, Don't Quietly Fade
Screwtape · 2023-11-13T23:30:25.308Z · comments (11)
Survey: How Do Elite Chinese Students Feel About the Risks of AI?
Nick Corvino (nick-corvino) · 2024-09-02T18:11:11.867Z · comments (13)
Momentum of Light in Glass
Ben (ben-lang) · 2024-10-09T20:19:42.088Z · comments (44)
[link] Decomposing Agency — capabilities without desires
owencb · 2024-07-11T09:38:48.509Z · comments (32)
[link] Overcoming Bias Anthology
Arjun Panickssery (arjun-panickssery) · 2024-10-20T02:01:23.463Z · comments (12)
My experience using financial commitments to overcome akrasia
William Howard (william-howard) · 2024-04-15T22:57:32.574Z · comments (31)
What good is G-factor if you're dumped in the woods? A field report from a camp counselor.
Hastings (hastings-greer) · 2024-01-12T13:17:23.829Z · comments (22)
0. CAST: Corrigibility as Singular Target
Max Harms (max-harms) · 2024-06-07T22:29:12.934Z · comments (12)
[link] Fields that I reference when thinking about AI takeover prevention
Buck · 2024-08-13T23:08:54.950Z · comments (15)
← previous page (newer posts) · next page (older posts) →