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) →

Making Bad Decisions On Purpose
Screwtape · 2023-11-09T03:36:59.611Z · comments (8)
Exercise: Planmaking, Surprise Anticipation, and "Baba is You"
Raemon · 2024-02-24T20:33:49.574Z · comments (19)
AISC 2024 - Project Summaries
NickyP (Nicky) · 2023-11-27T22:32:23.555Z · comments (3)
[link] Spaced repetition for teaching two-year olds how to read (Interview)
Chipmonk · 2023-11-26T16:52:58.412Z · comments (9)
On ‘Responsible Scaling Policies’ (RSPs)
Zvi · 2023-12-05T16:10:06.310Z · comments (3)
What is the next level of rationality?
lsusr · 2023-12-12T08:14:14.846Z · comments (24)
Safety First: safety before full alignment. The deontic sufficiency hypothesis.
Chipmonk · 2024-01-03T17:55:19.825Z · comments (3)
Mechanistic Interpretability Workshop Happening at ICML 2024!
Neel Nanda (neel-nanda-1) · 2024-05-03T01:18:26.936Z · comments (6)
Misnaming and Other Issues with OpenAI's “Human Level” Superintelligence Hierarchy
Davidmanheim · 2024-07-15T05:50:17.770Z · comments (2)
SRE's review of Democracy
Martin Sustrik (sustrik) · 2024-08-03T07:20:01.483Z · comments (2)
Why the Best Writers Endure Isolation
Declan Molony (declan-molony) · 2024-07-16T05:58:25.032Z · comments (6)
[link] Web-surfing tips for strange times
eukaryote · 2024-05-31T07:10:25.805Z · comments (19)
Philosophers wrestling with evil, as a social media feed
David Gross (David_Gross) · 2024-06-03T22:25:22.507Z · comments (2)
D&D.Sci: The Mad Tyrant's Pet Turtles [Evaluation and Ruleset]
abstractapplic · 2024-04-09T14:01:34.426Z · comments (6)
[link] Contra Acemoglu on AI
Maxwell Tabarrok (maxwell-tabarrok) · 2024-06-28T13:13:15.796Z · comments (0)
How to do conceptual research: Case study interview with Caspar Oesterheld
Chi Nguyen · 2024-05-14T15:09:30.390Z · comments (5)
[link] JumpReLU SAEs + Early Access to Gemma 2 SAEs
Senthooran Rajamanoharan (SenR) · 2024-07-19T16:10:54.664Z · comments (10)
The Mom Test: Summary and Thoughts
Adam Zerner (adamzerner) · 2024-04-18T03:34:21.020Z · comments (3)
[link] Designing for a single purpose
Itay Dreyfus (itay-dreyfus) · 2024-05-07T14:11:22.242Z · comments (12)
Some Experiments I'd Like Someone To Try With An Amnestic
johnswentworth · 2024-05-04T22:04:19.692Z · comments (33)
4. Existing Writing on Corrigibility
Max Harms (max-harms) · 2024-06-10T14:08:35.590Z · comments (13)
shortest goddamn bayes guide ever
lukehmiles (lcmgcd) · 2024-05-10T07:06:23.734Z · comments (8)
Extended Interview with Zhukeepa on Religion
Ben Pace (Benito) · 2024-08-18T03:19:05.625Z · comments (59)
Caring about excellence
owencb · 2024-07-22T14:24:37.892Z · comments (4)
How do we know that "good research" is good? (aka "direct evaluation" vs "eigen-evaluation")
Ruby · 2024-07-19T00:31:38.332Z · comments (21)
Run evals on base models too!
orthonormal · 2024-04-04T18:43:25.468Z · comments (6)
[link] "If we go extinct due to misaligned AI, at least nature will continue, right? ... right?"
plex (ete) · 2024-05-18T14:09:53.014Z · comments (23)
What distinguishes "early", "mid" and "end" games?
Raemon · 2024-06-21T17:41:30.816Z · comments (22)
Graceful Degradation
Screwtape · 2024-11-05T23:57:53.362Z · comments (2)
Demis Hassabis and Geoffrey Hinton Awarded Nobel Prizes
Anna Gajdova (anna-gajdova) · 2024-10-09T12:56:24.856Z · comments (14)
Toward Safety Case Inspired Basic Research
Lucas Teixeira · 2024-10-31T23:06:32.854Z · comments (2)
D&D.Sci Coliseum: Arena of Data Evaluation and Ruleset
aphyer · 2024-10-29T01:21:03.075Z · comments (10)
Environmental allergies are curable? (Sublingual immunotherapy)
Chipmonk · 2023-12-26T19:05:08.880Z · comments (10)
2023 Prediction Evaluations
Zvi · 2024-01-08T14:40:07.377Z · comments (0)
Value learning in the absence of ground truth
Joel_Saarinen (joel_saarinen) · 2024-02-05T18:56:02.260Z · comments (8)
Sora What
Zvi · 2024-02-22T18:10:05.397Z · comments (3)
How to safely use an optimizer
Simon Fischer (SimonF) · 2024-03-28T16:11:01.277Z · comments (21)
[link] on neodymium magnets
bhauth · 2024-01-30T15:58:24.088Z · comments (6)
Critiques of the AI control agenda
Jozdien · 2024-02-14T19:25:04.105Z · comments (14)
[link] Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities
porby · 2024-02-02T05:49:11.189Z · comments (1)
[link] Constructive Cauchy sequences vs. Dedekind cuts
jessicata (jessica.liu.taylor) · 2024-03-14T23:04:07.300Z · comments (23)
Goodbye, Shoggoth: The Stage, its Animatronics, & the Puppeteer – a New Metaphor
RogerDearnaley (roger-d-1) · 2024-01-09T20:42:28.349Z · comments (8)
[link] Five projects from AI Safety Hub Labs 2023
charlie_griffin (cjgriffin) · 2023-11-08T19:19:37.759Z · comments (1)
On the Proposed California SB 1047
Zvi · 2024-02-12T16:40:04.854Z · comments (18)
[link] If Clarity Seems Like Death to Them
Zack_M_Davis · 2023-12-30T17:40:42.622Z · comments (191)
D&D.Sci(-fi): Colonizing the SuperHyperSphere
abstractapplic · 2024-01-12T23:36:54.248Z · comments (23)
The predictive power of dissipative adaptation
dr_s · 2023-12-17T14:01:31.568Z · comments (14)
[link] The Leeroy Jenkins principle: How faulty AI could guarantee "warning shots"
titotal (lombertini) · 2024-01-14T15:03:21.087Z · comments (6)
Thoughts on "The Offense-Defense Balance Rarely Changes"
Cullen (Cullen_OKeefe) · 2024-02-12T03:26:50.662Z · comments (4)
AI doing philosophy = AI generating hands?
Wei Dai (Wei_Dai) · 2024-01-15T09:04:39.659Z · comments (22)
← previous page (newer posts) · next page (older posts) →