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) →

Announcing the PIBBSS Symposium '24!
DusanDNesic · 2024-09-03T11:19:47.568Z · comments (0)
Economics Roundup #4
Zvi · 2024-10-15T13:20:06.923Z · comments (4)
Lab governance reading list
Zach Stein-Perlman · 2024-10-25T18:00:28.346Z · comments (3)
[link] To Be Born in a Bag
Niko_McCarty (niko-2) · 2024-10-06T17:21:00.605Z · comments (1)
[link] Update on the Mysterious Trump Buyers on Polymarket
Annapurna (jorge-velez) · 2024-11-04T19:22:06.540Z · comments (9)
Why I'm bearish on mechanistic interpretability: the shards are not in the network
tailcalled · 2024-09-13T17:09:25.407Z · comments (40)
[link] Fragile, Robust, and Antifragile Preference Satisfaction
adamShimi · 2024-11-02T17:25:55.986Z · comments (0)
Review: “The Case Against Reality”
David Gross (David_Gross) · 2024-10-29T13:13:29.643Z · comments (9)
D/acc AI Security Salon
Allison Duettmann (allison-duettmann) · 2024-10-19T22:17:57.067Z · comments (0)
Looking for Goal Representations in an RL Agent - Update Post
CatGoddess · 2024-08-28T16:42:19.367Z · comments (0)
Why Reflective Stability is Important
Johannes C. Mayer (johannes-c-mayer) · 2024-09-05T15:28:19.913Z · comments (2)
What program structures enable efficient induction?
Daniel C (harper-owen) · 2024-09-05T10:12:14.058Z · comments (4)
Word Spaghetti
Gordon Seidoh Worley (gworley) · 2024-10-23T05:39:20.105Z · comments (9)
Advisors for Smaller Major Donors?
jefftk (jkaufman) · 2024-11-06T14:30:06.187Z · comments (2)
Can Large Language Models effectively identify cybersecurity risks?
emile delcourt (emile-delcourt) · 2024-08-30T20:20:21.345Z · comments (0)
[link] Should Sports Betting Be Banned?
Maxwell Tabarrok (maxwell-tabarrok) · 2024-09-21T14:13:35.404Z · comments (2)
Bridging the VLM and mech interp communities for multimodal interpretability
Sonia Joseph (redhat) · 2024-10-28T14:41:41.969Z · comments (5)
Avoiding the Bog of Moral Hazard for AI
Nathan Helm-Burger (nathan-helm-burger) · 2024-09-13T21:24:34.137Z · comments (12)
"Real AGI"
Seth Herd · 2024-09-13T14:13:24.124Z · comments (20)
In the Name of All That Needs Saving
pleiotroth · 2024-11-07T15:26:12.252Z · comments (2)
Automating LLM Auditing with Developmental Interpretability
htlou · 2024-09-04T15:50:04.337Z · comments (0)
[question] Is there any rigorous work on using anthropic uncertainty to prevent situational awareness / deception?
David Scott Krueger (formerly: capybaralet) (capybaralet) · 2024-09-04T12:40:07.678Z · answers+comments (7)
[link] Four Levels of Voting Methods
hive · 2024-09-26T18:15:00.565Z · comments (3)
[question] Does the "ancient wisdom" argument have any validity? If a particular teaching or tradition is old, to what extent does this make it more trustworthy?
SpectrumDT · 2024-11-04T15:20:14.822Z · answers+comments (42)
[link] Instruction Following without Instruction Tuning
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-09-24T13:49:09.078Z · comments (0)
OpenAI defected, but we can take honest actions
Remmelt (remmelt-ellen) · 2024-10-21T08:41:25.728Z · comments (15)
[link] GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning
ChengCheng (ccstan99) · 2024-11-01T00:10:50.718Z · comments (0)
[link] AlignedCut: Visual Concepts Discovery on Brain-Guided Universal Feature Space
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-09-14T23:23:26.296Z · comments (1)
[link] some questionable space launch guns
bhauth · 2024-10-13T22:52:26.418Z · comments (0)
My career exploration: Tools for building confidence
lynettebye · 2024-09-13T11:37:55.843Z · comments (0)
Is Text Watermarking a lost cause?
egor.timatkov · 2024-10-01T16:20:51.113Z · comments (13)
[link] Jonothan Gorard:The territory is isomorphic to an equivalence class of its maps
Daniel C (harper-owen) · 2024-09-07T10:04:47.840Z · comments (18)
[question] Is this voting system strategy proof?
Donald Hobson (donald-hobson) · 2024-09-06T20:44:46.691Z · answers+comments (9)
[link] Why Swiss watches and Taylor Swift are AGI-proof
Kevin Kohler (KevinKohler) · 2024-09-05T13:23:27.033Z · comments (11)
Reducing global AI competition through the Commerce Control List and Immigration reform: a dual-pronged approach
Ben Smith (ben-smith) · 2024-09-03T05:28:24.549Z · comments (2)
[link] Why good things often don’t lead to better outcomes
DMMF · 2024-09-19T16:37:07.778Z · comments (1)
Slave Morality: A place for every man and every man in his place
Martin Sustrik (sustrik) · 2024-09-19T04:20:04.491Z · comments (7)
[link] My lukewarm take on GLP-1 agonists
George3d6 · 2024-08-26T12:34:27.929Z · comments (0)
Review: Dr Stone
ProgramCrafter (programcrafter) · 2024-09-29T10:35:53.175Z · comments (5)
Thinking in 2D
sarahconstantin · 2024-10-20T19:30:05.842Z · comments (0)
The Logistics of Distribution of Meaning: Against Epistemic Bureaucratization
Sahil · 2024-11-07T05:27:20.276Z · comments (0)
Physical Therapy Sucks (but have you tried hiding it in some peanut butter?)
Declan Molony (declan-molony) · 2024-09-10T05:54:47.000Z · comments (12)
Hiring a writer to co-author with me (Spencer Greenberg for ClearerThinking.org)
spencerg · 2024-10-27T17:34:50.479Z · comments (0)
[question] Is there a CFAR handbook audio option?
FinalFormal2 · 2024-10-26T17:08:36.480Z · answers+comments (0)
Interview with Robert Kralisch on Simulators
WillPetillo · 2024-08-26T05:49:15.543Z · comments (0)
Appealing to the Public
jefftk (jkaufman) · 2024-10-23T19:00:07.669Z · comments (0)
Announcing the Ultimate Jailbreaking Championship
InnerHufflepuff (grayswan) · 2024-09-04T00:35:31.234Z · comments (1)
Join a LessWrong Team for the Unaging System Challenge
Crissman · 2024-10-23T06:01:08.018Z · comments (5)
[link] Where is the Learn Everything System?
Shoshannah Tekofsky (DarkSym) · 2024-09-27T21:30:16.379Z · comments (8)
[link] Levers for Biological Progress - A Response to "Machines of Loving Grace"
Niko_McCarty (niko-2) · 2024-11-01T16:35:08.221Z · comments (0)
← previous page (newer posts) · next page (older posts) →