LessWrong 2.0 Reader

View: New · Old · Top

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

next page (older posts) →

AGI Ruin: A List of Lethalities
Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2022-06-05T22:05:52.224Z · comments (690)
Where I agree and disagree with Eliezer
paulfchristiano · 2022-06-19T19:15:55.698Z · comments (219)
What an actually pessimistic containment strategy looks like
lc · 2022-04-05T00:19:50.212Z · comments (138)
SolidGoldMagikarp (plus, prompt generation)
Jessica Rumbelow (jessica-cooper) · 2023-02-05T22:02:35.854Z · comments (204)
The Waluigi Effect (mega-post)
Cleo Nardo (strawberry calm) · 2023-03-03T03:22:08.619Z · comments (187)
[link] Simulators
janus · 2022-09-02T12:45:33.723Z · comments (161)
Rationalism before the Sequences
Eric Raymond (eric-raymond) · 2021-03-30T14:04:15.254Z · comments (81)
Making Vaccine
johnswentworth · 2021-02-03T20:24:18.756Z · comments (249)
Let’s think about slowing down AI
KatjaGrace · 2022-12-22T17:40:04.787Z · comments (183)
The Redaction Machine
Ben (ben-lang) · 2022-09-20T22:03:15.309Z · comments (46)
The Talk: a brief explanation of sexual dimorphism
Malmesbury (Elmer of Malmesbury) · 2023-09-18T16:23:56.073Z · comments (72)
[link] Luck based medicine: my resentful story of becoming a medical miracle
Elizabeth (pktechgirl) · 2022-10-16T17:40:03.702Z · comments (119)
What 2026 looks like
Daniel Kokotajlo (daniel-kokotajlo) · 2021-08-06T16:14:49.772Z · comments (150)
Losing the root for the tree
Adam Zerner (adamzerner) · 2022-09-20T04:53:53.435Z · comments (30)
[link] How much do you believe your results?
Eric Neyman (UnexpectedValues) · 2023-05-06T20:31:31.277Z · comments (14)
It’s Probably Not Lithium
Natália (Natália Mendonça) · 2022-06-28T21:24:10.246Z · comments (186)
Counter-theses on Sleep
Natália (Natália Mendonça) · 2022-03-21T23:21:07.943Z · comments (131)
How To Write Quickly While Maintaining Epistemic Rigor
johnswentworth · 2021-08-28T17:52:21.692Z · comments (38)
Steering GPT-2-XL by adding an activation vector
TurnTrout · 2023-05-13T18:42:41.321Z · comments (97)
(My understanding of) What Everyone in Technical Alignment is Doing and Why
Thomas Larsen (thomas-larsen) · 2022-08-29T01:23:58.073Z · comments (89)
[link] The ants and the grasshopper
Richard_Ngo (ricraz) · 2023-06-04T22:00:04.577Z · comments (35)
Focus on the places where you feel shocked everyone's dropping the ball
So8res · 2023-02-02T00:27:55.687Z · comments (60)
chinchilla's wild implications
nostalgebraist · 2022-07-31T01:18:28.254Z · comments (128)
[link] Douglas Hofstadter changes his mind on Deep Learning & AI risk (June 2023)?
gwern · 2023-07-03T00:48:47.131Z · comments (54)
[link] It Looks Like You're Trying To Take Over The World
gwern · 2022-03-09T16:35:35.326Z · comments (120)
Significantly Enhancing Adult Intelligence With Gene Editing May Be Possible
GeneSmith · 2023-12-12T18:14:51.438Z · comments (162)
Bing Chat is blatantly, aggressively misaligned
evhub · 2023-02-15T05:29:45.262Z · comments (167)
[link] Reflections on six months of fatherhood
jasoncrawford · 2022-01-31T05:28:09.154Z · comments (24)
[link] Things I Learned by Spending Five Thousand Hours In Non-EA Charities
jenn (pixx) · 2023-06-01T20:48:03.940Z · comments (34)
DeepMind alignment team opinions on AGI ruin arguments
Vika · 2022-08-12T21:06:40.582Z · comments (37)
[link] Statement on AI Extinction - Signed by AGI Labs, Top Academics, and Many Other Notable Figures
Dan H (dan-hendrycks) · 2023-05-30T09:05:25.986Z · comments (77)
Lies Told To Children
Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2022-04-14T11:25:10.282Z · comments (94)
Counterarguments to the basic AI x-risk case
KatjaGrace · 2022-10-14T13:00:05.903Z · comments (124)
[link] A Mechanistic Interpretability Analysis of Grokking
Neel Nanda (neel-nanda-1) · 2022-08-15T02:41:36.245Z · comments (47)
You Are Not Measuring What You Think You Are Measuring
johnswentworth · 2022-09-20T20:04:22.899Z · comments (44)
GPTs are Predictors, not Imitators
Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2023-04-08T19:59:13.601Z · comments (88)
Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover
Ajeya Cotra (ajeya-cotra) · 2022-07-18T19:06:14.670Z · comments (94)
My Objections to "We’re All Gonna Die with Eliezer Yudkowsky"
Quintin Pope (quintin-pope) · 2023-03-21T00:06:07.889Z · comments (218)
Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment
elspood · 2022-06-21T23:55:39.918Z · comments (42)
Noting an error in Inadequate Equilibria
Matthew Barnett (matthew-barnett) · 2023-02-08T01:33:33.715Z · comments (56)
Accounting For College Costs
johnswentworth · 2022-04-01T17:28:19.409Z · comments (41)
How it feels to have your mind hacked by an AI
blaked · 2023-01-12T00:33:18.866Z · comments (219)
What DALL-E 2 can and cannot do
Swimmer963 (Miranda Dixon-Luinenburg) (Swimmer963) · 2022-05-01T23:51:22.310Z · comments (303)
Taboo "Outside View"
Daniel Kokotajlo (daniel-kokotajlo) · 2021-06-17T09:36:49.855Z · comments (33)
Reward is not the optimization target
TurnTrout · 2022-07-25T00:03:18.307Z · comments (122)
How To Get Into Independent Research On Alignment/Agency
johnswentworth · 2021-11-19T00:00:21.600Z · comments (38)
There is way too much serendipity
Malmesbury (Elmer of Malmesbury) · 2024-01-19T19:37:57.068Z · comments (56)
MIRI announces new "Death With Dignity" strategy
Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2022-04-02T00:43:19.814Z · comments (543)
Shutting Down the Lightcone Offices
habryka (habryka4) · 2023-03-14T22:47:51.539Z · comments (93)
Lessons I've Learned from Self-Teaching
TurnTrout · 2021-01-23T19:00:55.559Z · comments (74)
next page (older posts) →