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) →

[link] My Experience With A Magnet Implant
Vale · 2025-01-07T03:01:21.410Z · comments (2)
Do Antidepressants work? (First Take)
Jacob Goldsmith (jacgoldsm) · 2025-01-12T17:11:55.417Z · comments (8)
[question] Recommendations on communities that discuss AI applications in society
Annapurna (jorge-velez) · 2024-12-24T13:37:49.821Z · answers+comments (2)
Meditation insights as phase shifts in your self-model
Jonas Hallgren · 2025-01-07T10:09:35.854Z · comments (1)
[link] Deconstructing arguments against AI art
DMMF · 2024-12-27T19:40:13.015Z · comments (5)
[link] Our new video about goal misgeneralization, plus an apology
Writer · 2025-01-14T14:07:21.648Z · comments (0)
[question] How do you decide to phrase predictions you ask of others? (and how do you make your own?)
CstineSublime · 2025-01-10T02:44:26.737Z · answers+comments (0)
[question] Can private companies test LVTs?
Yair Halberstadt (yair-halberstadt) · 2025-01-02T11:08:07.352Z · answers+comments (0)
[link] AI Forecasting Benchmark: Congratulations to Q4 Winners + Q1 Practice Questions Open
ChristianWilliams · 2025-01-10T03:02:05.856Z · comments (0)
The Robot, the Puppet-master, and the Psychohistorian
WillPetillo · 2024-12-28T00:12:08.824Z · comments (2)
Ann Altman has filed a lawsuit in US federal court alleging that she was sexually abused by Sam Altman
quanticle · 2025-01-08T14:59:24.140Z · comments (3)
[link] Example of GPU-accelerated scientific computing with PyTorch
Tahp · 2025-01-01T23:01:04.606Z · comments (0)
[question] Why is neuron count of human brain relevant to AI timelines?
samuelshadrach (xpostah) · 2024-12-24T05:15:58.839Z · answers+comments (7)
[link] Streamlining my voice note process
Vlad Sitalo (harcisis) · 2024-12-26T06:04:01.990Z · comments (1)
Zombies among us
Declan Molony (declan-molony) · 2024-12-31T05:14:07.929Z · comments (3)
6. Increase Intelligence: Welcome AI Players
Allison Duettmann (allison-duettmann) · 2025-01-02T19:06:01.521Z · comments (1)
[link] How to Do a PhD (in AI Safety)
Lewis Hammond (lewis-hammond-1) · 2025-01-05T16:57:35.409Z · comments (0)
Speedrunning Rationality: Day II
aproteinengine · 2025-01-06T03:59:25.488Z · comments (3)
Generating Cognateful Sentences with Large Language Models
vkethana (vijay-k) · 2025-01-06T18:40:09.564Z · comments (0)
[link] AI Safety at the Frontier: Paper Highlights, December '24
gasteigerjo · 2025-01-11T22:54:02.625Z · comments (1)
Cast it into the fire! Destroy it!
Aram Panasenco (panasenco) · 2025-01-13T07:30:19.356Z · comments (9)
Logic vs intuition <=> algorithm vs ML
pchvykov · 2025-01-04T09:06:51.822Z · comments (0)
Speedrunning Rationality: Day I
aproteinengine · 2025-01-04T14:28:49.220Z · comments (0)
No, the Polymarket price does not mean we can immediately conclude what the probability of a bird flu pandemic is. We also need to know the interest rate!
Christopher King (christopher-king) · 2024-12-28T16:05:47.037Z · comments (8)
Why abandon “probability is in the mind” when it comes to quantum dynamics?
Maxwell Peterson (maxwell-peterson) · 2025-01-14T15:53:55.548Z · comments (0)
A proposal for iterated interpretability with known-interpretable narrow AIs
Peter Berggren (peter-berggren) · 2025-01-11T14:43:05.423Z · comments (0)
4. Uphold Voluntarism: Physical Defense
Allison Duettmann (allison-duettmann) · 2025-01-02T19:04:53.675Z · comments (2)
Dishbrain and implications.
RussellThor · 2024-12-29T10:42:43.912Z · comments (0)
Linkpost: Look at the Water
J Bostock (Jemist) · 2024-12-30T19:49:04.107Z · comments (3)
[link] Better antibodies by engineering targets, not engineering antibodies (Nabla Bio)
Abhishaike Mahajan (abhishaike-mahajan) · 2025-01-13T15:05:35.261Z · comments (0)
Activation Magnitudes Matter On Their Own: Insights from Language Model Distributional Analysis
Matt Levinson · 2025-01-10T06:53:02.228Z · comments (0)
Good Fortune and Many Worlds
Jonah Wilberg (jrwilb@googlemail.com) · 2024-12-27T13:21:43.142Z · comments (0)
[link] Independent research article analyzing consistent self-reports of experience in ChatGPT and Claude
rife (edgar-muniz) · 2025-01-06T17:34:01.505Z · comments (17)
Some implications of radical empathy
MichaelStJules · 2025-01-07T16:10:16.755Z · comments (0)
Thoughts on the In-Context Scheming AI Experiment
ExCeph · 2025-01-09T02:19:09.558Z · comments (0)
5. Uphold Voluntarism: Digital Defense
Allison Duettmann (allison-duettmann) · 2025-01-02T19:05:33.963Z · comments (0)
3. Improve Cooperation: Better Technologies
Allison Duettmann (allison-duettmann) · 2025-01-02T19:03:16.588Z · comments (2)
[question] 2025 Alignment Predictions
anaguma · 2025-01-02T05:37:36.912Z · answers+comments (3)
Have frontier AI systems surpassed the self-replicating red line?
nsage (wheelspawn) · 2025-01-11T05:31:31.672Z · comments (0)
[question] Are Sparse Autoencoders a good idea for AI control?
Gerard Boxo (gerard-boxo) · 2024-12-26T17:34:55.617Z · answers+comments (2)
Gothenburg LW / ACX meetup
Stefan (stefan-1) · 2025-01-08T21:39:18.309Z · comments (0)
Governance Course - Week 1 Reflections
la .alis. (Diatom) · 2025-01-09T04:48:27.502Z · comments (0)
[link] Expevolu, Part II: Buying land to create countries
Fernando · 2025-01-09T21:11:11.780Z · comments (0)
[link] The Golden Opportunity for American AI
Annapurna (jorge-velez) · 2025-01-04T10:26:05.430Z · comments (8)
[link] The Economics & Practicality of Starting Mars Colonization
Zero Contradictions · 2024-12-26T10:56:26.019Z · comments (1)
I Recommend More Training Rationales
Gianluca Calcagni (gianluca-calcagni) · 2024-12-31T14:06:44.007Z · comments (0)
[link] What are polysemantic neurons?
Vishakha (vishakha-agrawal) · 2025-01-08T07:35:42.758Z · comments (0)
Can we have Epiphanies and Eureka moments more frequently?
CstineSublime · 2025-01-08T02:20:26.897Z · comments (0)
Algorithmic Asubjective Anthropics, Cartesian Subjective Anthropics
Lorec · 2024-12-27T01:58:39.880Z · comments (0)
Duplicate token neurons in the first layer of gpt2-small
Alex Gibson · 2024-12-27T04:21:55.896Z · comments (0)
← previous page (newer posts) · next page (older posts) →