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) →

If a little is good, is more better?
DanielFilan · 2023-11-04T07:10:05.943Z · comments (16)
[link] OpenAI Superalignment: Weak-to-strong generalization
Dalmert · 2023-12-14T19:47:24.347Z · comments (3)
[question] How to Model the Future of Open-Source LLMs?
Joel Burget (joel-burget) · 2024-04-19T14:28:00.175Z · answers+comments (9)
A Review of In-Context Learning Hypotheses for Automated AI Alignment Research
alamerton · 2024-04-18T18:29:33.892Z · comments (4)
[link] **In defence of Helen Toner, Adam D'Angelo, and Tasha McCauley**
mrtreasure · 2023-12-06T02:02:32.004Z · comments (3)
[question] Impressions from base-GPT-4?
mishka · 2023-11-08T05:43:23.001Z · answers+comments (25)
[link] Executive Dysfunction 101
DaystarEld · 2024-05-23T12:43:13.785Z · comments (1)
Improving SAE's by Sqrt()-ing L1 & Removing Lowest Activating Features
Logan Riggs (elriggs) · 2024-03-15T16:30:00.744Z · comments (5)
Testing for consequence-blindness in LLMs using the HI-ADS unit test.
David Scott Krueger (formerly: capybaralet) (capybaralet) · 2023-11-24T23:35:29.560Z · comments (2)
Decent plan prize announcement (1 paragraph, $1k)
lukehmiles (lcmgcd) · 2024-01-12T06:27:44.495Z · comments (19)
[link] Was a Subway in New York City Inevitable?
Jeffrey Heninger (jeffrey-heninger) · 2024-03-30T00:53:21.314Z · comments (4)
Useful starting code for interpretability
eggsyntax · 2024-02-13T23:13:47.940Z · comments (2)
Language and Capabilities: Testing LLM Mathematical Abilities Across Languages
Ethan Edwards · 2024-04-04T13:18:54.909Z · comments (2)
A Basic Economics-Style Model of AI Existential Risk
Rubi J. Hudson (Rubi) · 2024-06-24T20:26:09.744Z · comments (3)
Anomalous Concept Detection for Detecting Hidden Cognition
Paul Colognese (paul-colognese) · 2024-03-04T16:52:52.568Z · comments (3)
[link] Let's Design A School, Part 2.3 School as Education - The Curriculum (Phase 2, Specific)
Sable · 2024-05-15T20:58:50.981Z · comments (0)
[link] Compensating for Life Biases
Jonathan Moregård (JonathanMoregard) · 2024-01-09T14:39:14.229Z · comments (6)
Distillation of 'Do language models plan for future tokens'
TheManxLoiner · 2024-06-27T20:57:34.351Z · comments (2)
[link] Alignment work in anomalous worlds
Tamsin Leake (carado-1) · 2023-12-16T19:34:26.202Z · comments (4)
Evolution did a surprising good job at aligning humans...to social status
Eli Tyre (elityre) · 2024-03-10T19:34:52.544Z · comments (37)
An evaluation of Helen Toner’s interview on the TED AI Show
PeterH · 2024-06-06T17:39:40.800Z · comments (2)
Utility is not the selection target
tailcalled · 2023-11-04T22:48:20.713Z · comments (1)
A conceptual precursor to today's language machines [Shannon]
Bill Benzon (bill-benzon) · 2023-11-15T13:50:51.226Z · comments (6)
[question] Would you have a baby in 2024?
martinkunev · 2023-12-25T01:52:04.358Z · answers+comments (76)
[link] AI Alignment [Progress] this Week (11/05/2023)
Logan Zoellner (logan-zoellner) · 2023-11-07T13:26:21.995Z · comments (0)
Scientific Method
Andrij “Androniq” Ghorbunov (andrij-androniq-ghorbunov) · 2024-02-18T21:06:45.228Z · comments (4)
Weeping Agents
pleiotroth · 2024-06-06T12:18:54.978Z · comments (2)
[link] Was Partisanship Good for the Environmental Movement?
Jeffrey Heninger (jeffrey-heninger) · 2024-05-15T17:30:54.796Z · comments (0)
Distinctions when Discussing Utility Functions
ozziegooen · 2024-03-09T20:14:03.592Z · comments (7)
[link] Secret US natsec project with intel revealed
Nathan Helm-Burger (nathan-helm-burger) · 2024-05-25T04:22:11.624Z · comments (0)
Defense Against The Dark Arts: An Introduction
Lyrongolem (david-xiao) · 2023-12-25T06:36:06.278Z · comments (36)
aintelope project update
Gunnar_Zarncke · 2024-02-08T18:32:00.000Z · comments (2)
Paper Summary: The Koha Code - A Biological Theory of Memory
jakej (jake-jenks) · 2023-12-30T22:37:13.865Z · comments (2)
How Congressional Offices Process Constituent Communication
Tristan Williams (tristan-williams) · 2024-07-02T12:38:41.472Z · comments (0)
[link] Eric Schmidt on recursive self-improvement
nikola (nikolaisalreadytaken) · 2023-11-05T19:05:15.416Z · comments (3)
My Alignment "Plan": Avoid Strong Optimisation and Align Economy
VojtaKovarik · 2024-01-31T17:03:34.778Z · comments (9)
[question] What percent of the sun would a Dyson Sphere cover?
Raemon · 2024-07-03T17:27:50.826Z · answers+comments (26)
Foresight Institute: 2023 Progress & 2024 Plans for funding beneficial technology development
Allison Duettmann (allison-duettmann) · 2023-11-22T22:09:16.956Z · comments (1)
A bet on critical periods in neural networks
kave · 2023-11-06T23:21:17.279Z · comments (1)
[question] Could there be "natural impact regularization" or "impact regularization by default"?
tailcalled · 2023-12-01T22:01:46.062Z · answers+comments (6)
Seeking Mechanism Designer for Research into Internalizing Catastrophic Externalities
c.trout (ctrout) · 2024-09-11T15:09:48.019Z · comments (2)
Improving Model-Written Evals for AI Safety Benchmarking
Sunishchal Dev (sunishchal-dev) · 2024-10-15T18:25:08.179Z · comments (0)
the Daydication technique
chaosmage · 2024-10-18T21:47:46.448Z · comments (0)
[link] "25 Lessons from 25 Years of Marriage" by honorary rationalist Ferrett Steinmetz
CronoDAS · 2024-10-02T22:42:30.509Z · comments (2)
SAEs you can See: Applying Sparse Autoencoders to Clustering
Robert_AIZI · 2024-10-28T14:48:16.744Z · comments (0)
Technology path dependence and evaluating expertise
bhauth · 2024-01-05T19:21:23.302Z · comments (2)
[link] Robert Caro And Mechanistic Models In Biography
adamShimi · 2024-07-14T10:56:42.763Z · comments (5)
[link] The absence of self-rejection is self-acceptance
Chipmonk · 2023-12-21T21:54:52.116Z · comments (1)
Building Trust in Strategic Settings
StrivingForLegibility · 2023-12-28T22:12:24.024Z · comments (0)
[link] Truth is Universal: Robust Detection of Lies in LLMs
Lennart Buerger · 2024-07-19T14:07:25.162Z · comments (3)
← previous page (newer posts) · next page (older posts) →