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) →

Domain-specific SAEs
jacob_drori (jacobcd52) · 2024-10-07T20:15:38.584Z · comments (0)
Superintelligence Can't Solve the Problem of Deciding What You'll Do
Vladimir_Nesov · 2024-09-15T21:03:28.077Z · comments (11)
An AI crash is our best bet for restricting AI
Remmelt (remmelt-ellen) · 2024-10-11T02:12:03.491Z · comments (1)
SAE features for refusal and sycophancy steering vectors
neverix · 2024-10-12T14:54:48.022Z · comments (4)
Do Sparse Autoencoders (SAEs) transfer across base and finetuned language models?
Taras Kutsyk · 2024-09-29T19:37:30.465Z · comments (7)
[link] Arithmetic Models: Better Than You Think
kqr · 2024-10-26T09:42:07.185Z · comments (4)
Why is there Nothing rather than Something?
Logan Zoellner (logan-zoellner) · 2024-10-26T12:37:50.204Z · comments (3)
[question] Seeking AI Alignment Tutor/Advisor: $100–150/hr
MrThink (ViktorThink) · 2024-10-05T21:28:16.491Z · answers+comments (3)
[link] Can a Bayesian Oracle Prevent Harm from an Agent? (Bengio et al. 2024)
mattmacdermott · 2024-09-01T07:46:26.647Z · comments (0)
Evaluating Solar
jefftk (jkaufman) · 2024-02-17T21:50:04.783Z · comments (5)
Exploring OpenAI's Latent Directions: Tests, Observations, and Poking Around
Johnny Lin (hijohnnylin) · 2024-01-31T06:01:27.969Z · comments (4)
[link] How to Upload a Mind (In Three Not-So-Easy Steps)
aggliu · 2023-11-13T18:13:32.893Z · comments (0)
Smartphone Etiquette: Suggestions for Social Interactions
Declan Molony (declan-molony) · 2024-06-04T06:01:03.336Z · comments (4)
Losing Metaphors: Zip and Paste
jefftk (jkaufman) · 2023-11-29T20:31:07.464Z · comments (6)
Ideas for Next-Generation Writing Platforms, using LLMs
ozziegooen · 2024-06-04T18:40:24.636Z · comments (4)
[link] Forecasting future gains due to post-training enhancements
elifland · 2024-03-08T02:11:57.228Z · comments (2)
[link] Agreeing With Stalin in Ways That Exhibit Generally Rationalist Principles
Zack_M_Davis · 2024-03-02T22:05:49.553Z · comments (22)
[link] my favourite Scott Sumner blog posts
DMMF · 2024-06-11T14:40:43.093Z · comments (0)
[link] Emotional issues often have an immediate payoff
Chipmonk · 2024-06-10T23:39:40.697Z · comments (2)
Evidential Correlations are Subjective, and it might be a problem
Martín Soto (martinsq) · 2024-03-07T18:37:54.105Z · comments (6)
Singular learning theory and bridging from ML to brain emulations
kave · 2023-11-01T21:31:54.789Z · comments (16)
Geometric Utilitarianism (And Why It Matters)
StrivingForLegibility · 2024-05-12T03:41:21.342Z · comments (2)
The Sequences on YouTube
Neil (neil-warren) · 2024-01-07T01:44:39.663Z · comments (9)
A list of all the deadlines in Biden's Executive Order on AI
Valentin Baltadzhiev (valentin-baltadzhiev) · 2023-11-01T17:14:31.074Z · comments (2)
The Limitations of GPT-4
p.b. · 2023-11-24T15:30:30.933Z · comments (12)
Quick takes on "AI is easy to control"
So8res · 2023-12-02T22:31:45.683Z · comments (49)
Meetup In a Box: Year In Review
Czynski (JacobKopczynski) · 2024-02-14T01:18:28.259Z · comments (0)
Three Types of Constraints in the Space of Agents
Nora_Ammann · 2024-01-15T17:27:27.560Z · comments (3)
Causality is Everywhere
silentbob · 2024-02-13T13:44:49.952Z · comments (12)
D&D.Sci Hypersphere Analysis Part 3: Beat it with Linear Algebra
aphyer · 2024-01-16T22:44:52.424Z · comments (1)
Vote in the LessWrong review! (LW 2022 Review voting phase)
habryka (habryka4) · 2024-01-17T07:22:17.921Z · comments (9)
Taking Into Account Sentient Non-Humans in AI Ambitious Value Learning: Sentientist Coherent Extrapolated Volition
Adrià Moret (Adrià R. Moret) · 2023-12-02T14:07:29.992Z · comments (31)
Am I going insane or is the quality of education at top universities shockingly low?
ChrisRumanov (pseudonymous-ai) · 2023-11-20T03:53:30.056Z · comments (30)
What is the best argument that LLMs are shoggoths?
JoshuaFox · 2024-03-17T11:36:23.636Z · comments (22)
Bayesian inference without priors
DanielFilan · 2024-04-24T23:50:08.312Z · comments (8)
AI debate: test yourself against chess 'AIs'
Richard Willis · 2023-11-22T14:58:10.847Z · comments (35)
Links and brief musings for June
Kaj_Sotala · 2024-07-06T10:10:03.344Z · comments (0)
Facebook is Paying Me to Post
jefftk (jkaufman) · 2023-11-14T19:10:07.303Z · comments (5)
Why I think it's net harmful to do technical safety research at AGI labs
Remmelt (remmelt-ellen) · 2024-02-07T04:17:15.246Z · comments (24)
Consequentialism is a compass, not a judge
Neil (neil-warren) · 2024-04-13T10:47:44.980Z · comments (6)
Sleeping on Stage
jefftk (jkaufman) · 2024-10-22T00:50:07.994Z · comments (3)
Agent membranes/boundaries and formalizing “safety”
Chipmonk · 2024-01-03T17:55:21.018Z · comments (46)
[link] Attention on AI X-Risk Likely Hasn't Distracted from Current Harms from AI
Erich_Grunewald · 2023-12-21T17:24:16.713Z · comments (2)
[link] Positive visions for AI
L Rudolf L (LRudL) · 2024-07-23T20:15:26.064Z · comments (4)
The causal backbone conjecture
tailcalled · 2024-08-17T18:50:14.577Z · comments (0)
[question] Thoughts on Francois Chollet's belief that LLMs are far away from AGI?
O O (o-o) · 2024-06-14T06:32:48.170Z · answers+comments (17)
Talk: AI safety fieldbuilding at MATS
Ryan Kidd (ryankidd44) · 2024-06-23T23:06:37.623Z · comments (2)
Just because an LLM said it doesn't mean it's true: an illustrative example
dirk (abandon) · 2024-08-21T21:05:59.691Z · comments (12)
LessWrong email subscriptions?
Raemon · 2024-08-27T21:59:56.855Z · comments (6)
[link] Manifold Markets
PeterMcCluskey · 2024-02-02T17:48:36.630Z · comments (9)
← previous page (newer posts) · next page (older posts) →