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) →

Evidence against Learned Search in a Chess-Playing Neural Network
p.b. · 2024-09-13T11:59:55.634Z · comments (3)
U.S.-China Economic and Security Review Commission pushes Manhattan Project-style AI initiative
Phib · 2024-11-19T18:42:43.296Z · comments (7)
AI #84: Better Than a Podcast
Zvi · 2024-10-03T15:00:07.128Z · comments (7)
A Path out of Insufficient Views
Unreal · 2024-09-24T20:00:27.332Z · comments (46)
Safe Predictive Agents with Joint Scoring Rules
Rubi J. Hudson (Rubi) · 2024-10-09T16:38:16.535Z · comments (10)
Toward Safety Case Inspired Basic Research
Lucas Teixeira · 2024-10-31T23:06:32.854Z · comments (2)
[link] The Evals Gap
Marius Hobbhahn (marius-hobbhahn) · 2024-11-11T16:42:46.287Z · comments (7)
Secret Collusion: Will We Know When to Unplug AI?
schroederdewitt · 2024-09-16T16:07:01.119Z · comments (7)
Win/continue/lose scenarios and execute/replace/audit protocols
Buck · 2024-11-15T15:47:24.868Z · comments (2)
[link] On the Role of Proto-Languages
adamShimi · 2024-09-22T16:50:34.720Z · comments (1)
[link] How Likely Are Various Precursors of Existential Risk?
NunoSempere (Radamantis) · 2024-10-28T13:27:31.620Z · comments (4)
Neuroscience of human social instincts: a sketch
Steven Byrnes (steve2152) · 2024-11-22T16:16:52.552Z · comments (0)
A Qualitative Case for LTFF: Filling Critical Ecosystem Gaps
Linch · 2024-11-18T00:44:57.133Z · comments (2)
Reformative Hypocrisy, and Paying Close Enough Attention to Selectively Reward It.
Andrew_Critch · 2024-09-11T04:41:24.872Z · comments (11)
Parental Writing Selection Bias
jefftk (jkaufman) · 2024-10-13T14:00:03.225Z · comments (3)
How to Give in to Threats (without incentivizing them)
Mikhail Samin (mikhail-samin) · 2024-09-12T15:55:50.384Z · comments (26)
[link] The Mysterious Trump Buyers on Polymarket
Annapurna (jorge-velez) · 2024-10-18T13:26:25.565Z · comments (9)
How might we solve the alignment problem? (Part 1: Intro, summary, ontology)
Joe Carlsmith (joekc) · 2024-10-28T21:57:12.063Z · comments (5)
[question] If I wanted to spend WAY more on AI, what would I spend it on?
Logan Zoellner (logan-zoellner) · 2024-09-15T21:24:46.742Z · answers+comments (16)
[link] Anthropic's updated Responsible Scaling Policy
Zac Hatfield-Dodds (zac-hatfield-dodds) · 2024-10-15T16:46:48.727Z · comments (3)
[link] Prices are Bounties
Maxwell Tabarrok (maxwell-tabarrok) · 2024-10-12T14:51:40.689Z · comments (13)
Model evals for dangerous capabilities
Zach Stein-Perlman · 2024-09-23T11:00:00.866Z · comments (11)
[link] a space habitat design
bhauth · 2024-11-25T17:28:48.481Z · comments (12)
Claude Sonnet 3.5.1 and Haiku 3.5
Zvi · 2024-10-24T14:50:06.286Z · comments (9)
Applications of Chaos: Saying No (with Hastings Greer)
Elizabeth (pktechgirl) · 2024-09-21T16:30:07.415Z · comments (16)
Metastatic Cancer Treatment Since 2010: The Success Stories
sarahconstantin · 2024-11-04T22:50:09.386Z · comments (2)
[link] Can AI Outpredict Humans? Results From Metaculus's Q3 AI Forecasting Benchmark
ChristianWilliams · 2024-10-10T18:58:46.041Z · comments (2)
AI #82: The Governor Ponders
Zvi · 2024-09-19T13:30:04.863Z · comments (8)
Low Probability Estimation in Language Models
Gabriel Wu (gabriel-wu) · 2024-10-18T15:50:05.947Z · comments (0)
The Fragility of Life Hypothesis and the Evolution of Cooperation
KristianRonn · 2024-09-04T21:04:49.878Z · comments (6)
[Intuitive self-models] 7. Hearing Voices, and Other Hallucinations
Steven Byrnes (steve2152) · 2024-10-29T13:36:16.325Z · comments (2)
[link] cancer rates after gene therapy
bhauth · 2024-10-16T15:32:53.949Z · comments (0)
A Conflicted Linkspost
Screwtape · 2024-11-21T00:37:54.035Z · comments (0)
[link] Book review: Xenosystems
jessicata (jessica.liu.taylor) · 2024-09-16T20:17:56.670Z · comments (18)
Demis Hassabis and Geoffrey Hinton Awarded Nobel Prizes
Anna Gajdova (anna-gajdova) · 2024-10-09T12:56:24.856Z · comments (14)
An alternative approach to superbabies
Towards_Keeperhood (Simon Skade) · 2024-11-05T22:56:15.740Z · comments (19)
AI and the Technological Richter Scale
Zvi · 2024-09-04T14:00:08.625Z · comments (8)
[link] Active Recall and Spaced Repetition are Different Things
Saul Munn (saul-munn) · 2024-11-08T20:14:56.092Z · comments (2)
Conflating value alignment and intent alignment is causing confusion
Seth Herd · 2024-09-05T16:39:51.967Z · comments (18)
Interested in Cognitive Bootcamp?
Raemon · 2024-09-19T22:12:13.348Z · comments (0)
Dave Kasten's AGI-by-2027 vignette
davekasten · 2024-11-26T23:20:47.212Z · comments (8)
Evaluating the truth of statements in a world of ambiguous language.
Hastings (hastings-greer) · 2024-10-07T18:08:09.920Z · comments (19)
AI #91: Deep Thinking
Zvi · 2024-11-21T14:30:06.930Z · comments (9)
[link] [Paper Blogpost] When Your AIs Deceive You: Challenges with Partial Observability in RLHF
Leon Lang (leon-lang) · 2024-10-22T13:57:41.125Z · comments (0)
Looking back on the Future of Humanity Institute - Asterisk
jakeeaton · 2024-11-19T00:44:40.928Z · comments (0)
Which evals resources would be good?
Marius Hobbhahn (marius-hobbhahn) · 2024-11-16T14:24:48.012Z · comments (4)
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
Marcus Williams · 2024-11-07T15:39:06.854Z · comments (6)
Secular Solstice Round Up 2024
dspeyer · 2024-11-21T10:49:36.682Z · comments (13)
D&D.Sci Coliseum: Arena of Data Evaluation and Ruleset
aphyer · 2024-10-29T01:21:03.075Z · comments (12)
[link] Michael Dickens' Caffeine Tolerance Research
niplav · 2024-09-04T15:41:53.343Z · comments (3)
← previous page (newer posts) · next page (older posts) →