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) →

Circuits in Superposition: Compressing many small neural networks into one
Lucius Bushnaq (Lblack) · 2024-10-14T13:06:14.596Z · comments (8)
[link] OpenAI's CBRN tests seem unclear
LucaRighetti (Error404Dinosaur) · 2024-11-21T17:28:30.290Z · comments (6)
"The Solomonoff Prior is Malign" is a special case of a simpler argument
David Matolcsi (matolcsid) · 2024-11-17T21:32:34.711Z · comments (44)
BIG-Bench Canary Contamination in GPT-4
Jozdien · 2024-10-22T15:40:48.166Z · comments (13)
Why Don't We Just... Shoggoth+Face+Paraphraser?
Daniel Kokotajlo (daniel-kokotajlo) · 2024-11-19T20:53:52.084Z · comments (51)
[link] The Dangers of Mirrored Life
Niko_McCarty (niko-2) · 2024-12-12T20:58:32.750Z · comments (7)
A bird's eye view of ARC's research
Jacob_Hilton · 2024-10-23T15:50:06.123Z · comments (12)
Passages I Highlighted in The Letters of J.R.R.Tolkien
Ivan Vendrov (ivan-vendrov) · 2024-11-25T01:47:59.071Z · comments (10)
[link] Miles Brundage resigned from OpenAI, and his AGI readiness team was disbanded
garrison · 2024-10-23T23:40:57.180Z · comments (1)
The Dream Machine
sarahconstantin · 2024-12-05T00:00:05.796Z · comments (6)
What o3 Becomes by 2028
Vladimir_Nesov · 2024-12-22T12:37:20.929Z · comments (10)
The o1 System Card Is Not About o1
Zvi · 2024-12-13T20:30:08.048Z · comments (5)
Scissors Statements for President?
AnnaSalamon · 2024-11-06T10:38:21.230Z · comments (31)
Should CA, TX, OK, and LA merge into a giant swing state, just for elections?
Thomas Kwa (thomas-kwa) · 2024-11-06T23:01:48.992Z · comments (35)
You should consider applying to PhDs (soon!)
bilalchughtai (beelal) · 2024-11-29T20:33:12.462Z · comments (19)
DeepSeek beats o1-preview on math, ties on coding; will release weights
Zach Stein-Perlman · 2024-11-20T23:50:26.597Z · comments (23)
Sorry for the downtime, looks like we got DDosd
habryka (habryka4) · 2024-12-02T04:14:30.209Z · comments (13)
The Big Nonprofits Post
Zvi · 2024-11-29T16:10:06.938Z · comments (10)
[link] Announcing turntrout.com, my new digital home
TurnTrout · 2024-11-17T17:42:08.164Z · comments (24)
Ablations for “Frontier Models are Capable of In-context Scheming”
AlexMeinke (Paulawurm) · 2024-12-17T23:58:19.222Z · comments (1)
Hierarchical Agency: A Missing Piece in AI Alignment
Jan_Kulveit · 2024-11-27T05:49:04.241Z · comments (20)
AIs Will Increasingly Attempt Shenanigans
Zvi · 2024-12-16T15:20:05.652Z · comments (2)
A shortcoming of concrete demonstrations as AGI risk advocacy
Steven Byrnes (steve2152) · 2024-12-11T16:48:41.602Z · comments (27)
I turned decision theory problems into memes about trolleys
Tapatakt · 2024-10-30T20:13:29.589Z · comments (20)
LLMs can learn about themselves by introspection
Felix J Binder (fjb) · 2024-10-18T16:12:51.231Z · comments (38)
Why comparative advantage does not help horses
Sherrinford · 2024-09-30T22:27:57.450Z · comments (15)
Behavioral red-teaming is unlikely to produce clear, strong evidence that models aren't scheming
Buck · 2024-10-10T13:36:53.810Z · comments (4)
[link] Advice for journalists
Nathan Young · 2024-10-07T16:46:40.929Z · comments (53)
[link] How to replicate and extend our alignment faking demo
Fabien Roger (Fabien) · 2024-12-19T21:44:13.059Z · comments (0)
MIRI’s 2024 End-of-Year Update
Rob Bensinger (RobbBB) · 2024-12-03T04:33:47.499Z · comments (2)
Bigger Livers?
sarahconstantin · 2024-11-08T21:50:09.814Z · comments (13)
[link] Seven lessons I didn't learn from election day
Eric Neyman (UnexpectedValues) · 2024-11-14T18:39:07.053Z · comments (33)
You can, in fact, bamboozle an unaligned AI into sparing your life
David Matolcsi (matolcsid) · 2024-09-29T16:59:43.942Z · comments (171)
The "Think It Faster" Exercise
Raemon · 2024-12-11T19:14:10.427Z · comments (13)
The case for unlearning that removes information from LLM weights
Fabien Roger (Fabien) · 2024-10-14T14:08:04.775Z · comments (15)
[link] Anthropic: Three Sketches of ASL-4 Safety Case Components
Zach Stein-Perlman · 2024-11-06T16:00:06.940Z · comments (33)
[link] Finishing The SB-1047 Documentary In 6 Weeks
Michaël Trazzi (mtrazzi) · 2024-10-28T20:17:47.465Z · comments (5)
Takes on "Alignment Faking in Large Language Models"
Joe Carlsmith (joekc) · 2024-12-18T18:22:34.059Z · comments (8)
[link] Sabotage Evaluations for Frontier Models
David Duvenaud (david-duvenaud) · 2024-10-18T22:33:14.320Z · comments (55)
2024 Petrov Day Retrospective
Ben Pace (Benito) · 2024-09-28T21:30:14.952Z · comments (25)
Hire (or become) a Thinking Assistant / Body Double
Raemon · 2024-12-23T03:58:42.061Z · comments (23)
Science advances one funeral at a time
Cameron Berg (cameron-berg) · 2024-11-01T23:06:19.381Z · comments (9)
Catastrophic sabotage as a major threat model for human-level AI systems
evhub · 2024-10-22T20:57:11.395Z · comments (11)
LLMs Look Increasingly Like General Reasoners
eggsyntax · 2024-11-08T23:47:28.886Z · comments (45)
Zvi’s Thoughts on His 2nd Round of SFF
Zvi · 2024-11-20T13:40:08.092Z · comments (2)
2024 Unofficial LessWrong Census/Survey
Screwtape · 2024-12-02T05:30:53.019Z · comments (42)
A very strange probability paradox
notfnofn · 2024-11-22T14:01:36.587Z · comments (26)
The nihilism of NeurIPS
charlieoneill (kingchucky211) · 2024-12-20T23:58:11.858Z · comments (4)
Three Notions of "Power"
johnswentworth · 2024-10-30T06:10:08.326Z · comments (44)
Anvil Problems
Screwtape · 2024-11-13T22:57:41.974Z · comments (13)
← previous page (newer posts) · next page (older posts) →