LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

Sunday August 2, 12pm (PDT) — talks by jimrandomh, johnswenthworth, Daniel Filan, Jacobian
jacobjacob · 2020-07-30T23:55:44.712Z · comments (2)
Dealing with Curiosity-Stoppers
adamShimi · 2020-07-30T22:05:02.668Z · comments (6)
[question] What if memes are common in highly capable minds?
Daniel Kokotajlo (daniel-kokotajlo) · 2020-07-30T20:45:17.500Z · answers+comments (8)
PSA: Tagging is Awesome
abramdemski · 2020-07-30T17:52:14.047Z · comments (19)
Covid 7/30: Whack a Mole
Zvi · 2020-07-30T15:50:04.756Z · comments (4)
[question] Is the work on AI alignment relevant to GPT?
Richard_Kennaway · 2020-07-30T12:23:56.842Z · answers+comments (5)
[question] Would a halfway copied brain emulation be at risk of having different values/identity?
Ghatanathoah · 2020-07-30T05:43:30.772Z · answers+comments (8)
Rationalist Reading Group (Online)
AspiringRationalist · 2020-07-30T02:14:04.411Z · comments (1)
Attention is your scarcest resource
benkuhn · 2020-07-30T01:00:13.705Z · comments (4)
Learning the prior and generalization
evhub · 2020-07-29T22:49:42.696Z · comments (16)
What Failure Looks Like: Distilling the Discussion
Ben Pace (Benito) · 2020-07-29T21:49:17.255Z · comments (12)
New Paper on Herd Immunity Thresholds
Zvi · 2020-07-29T20:50:01.242Z · comments (17)
What a 20-year-lead in military tech might look like
Daniel Kokotajlo (daniel-kokotajlo) · 2020-07-29T20:10:09.303Z · comments (44)
Engaging Seriously with Short Timelines
deluks917 · 2020-07-29T19:21:31.641Z · comments (23)
[AN #110]: Learning features from human feedback to enable reward learning
rohinmshah · 2020-07-29T17:20:04.369Z · comments (2)
Structured Tasks for Language Models
Zachary Robertson (zachary-robertson) · 2020-07-29T14:17:59.478Z · comments (None)
The "best predictor is malicious optimiser" problem
Donald Hobson (donald-hobson) · 2020-07-29T11:49:20.234Z · comments (10)
Improving local governance in fragile states - practical lessons from the field
rockthecasbah · 2020-07-29T01:54:39.861Z · comments (3)
Parameters of Privacy
Raemon · 2020-07-29T01:18:54.662Z · comments (1)
Predictions for GPT-N
hippke · 2020-07-29T01:16:10.678Z · comments (31)
Tagging Open Call / Discussion Thread
Ruby · 2020-07-28T21:58:25.087Z · comments (120)
Wiki-Tag FAQ
Ruby · 2020-07-28T21:57:39.272Z · comments (6)
Tags Discussion/Talk Thread
Ruby · 2020-07-28T21:57:04.540Z · comments (81)
[question] What happens to variance as neural network training is scaled? What does it imply about "lottery tickets"?
abramdemski · 2020-07-28T20:22:14.066Z · answers+comments (4)
[question] How will internet forums like LW be able to defend against GPT-style spam?
ChristianKl · 2020-07-28T20:12:56.458Z · answers+comments (18)
[question] To what extent are the scaling properties of Transformer networks exceptional?
abramdemski · 2020-07-28T20:06:24.191Z · answers+comments (1)
The Conceited Folly of Certainty
Noah Blaff (Deep Dives) · 2020-07-28T19:56:26.888Z · comments (3)
The Curse of Cursory Idealism
Noah Blaff (Deep Dives) · 2020-07-28T19:56:09.253Z · comments (1)
[question] Does the lottery ticket hypothesis suggest the scaling hypothesis?
Daniel Kokotajlo (daniel-kokotajlo) · 2020-07-28T19:52:51.825Z · answers+comments (17)
[question] Probability that other architectures will scale as well as Transformers?
Daniel Kokotajlo (daniel-kokotajlo) · 2020-07-28T19:36:53.590Z · answers+comments (4)
[question] How should I back up and redo, in a publicly-edited article?
Jameson Quinn (jameson-quinn) · 2020-07-28T19:07:13.046Z · answers+comments (None)
Rereading Atlas Shrugged
Vaniver · 2020-07-28T18:54:45.272Z · comments (27)
[link] FHI Report: How Will National Security Considerations Affect Antitrust Decisions in AI? An Examination of Historical Precedents
Cullen_OKeefe · 2020-07-28T18:34:23.537Z · comments (None)
[link] Delegate a Forecast
Amandango · 2020-07-28T17:43:58.461Z · comments (25)
[link] Asset Prices Consistently Violate Efficient Market Hypothesis
Liron · 2020-07-28T14:21:15.220Z · comments (2)
[link] A community-curated repository of interesting GPT-3 stuff
Rudi C (rudi-c) · 2020-07-28T14:16:50.475Z · comments (None)
[question] Billionaire Economics
Virgil Kurkjian · 2020-07-28T03:01:33.743Z · answers+comments (30)
[question] What specific dangers arise when asking GPT-N to write an Alignment Forum post?
Matthew Barnett (matthew-barnett) · 2020-07-28T02:56:12.711Z · answers+comments (14)
The Future of Science
Richard_Ngo (ricraz) · 2020-07-28T02:43:37.503Z · comments (2)
Basic Conversational Coordination: Micro-coordination of Intention
Eli Tyre (elityre) · 2020-07-27T22:41:53.236Z · comments (7)
[updated] how does gpt2′s training corpus capture internet discussion?  not well
nostalgebraist · 2020-07-27T22:30:07.909Z · comments (3)
[link] AI and Efficiency
DragonGod · 2020-07-27T20:58:43.625Z · comments (1)
[link] The Rise of Commonsense Reasoning
DragonGod · 2020-07-27T19:01:16.068Z · comments (None)
Why You Might Want a New Way to Visualize Biases
dtm · 2020-07-27T17:30:45.065Z · comments (3)
Are we in an AI overhang?
Andy Jones (andyljones) · 2020-07-27T12:48:05.196Z · comments (94)
Generalizing the Power-Seeking Theorems
TurnTrout · 2020-07-27T00:28:25.677Z · comments (6)
Change the world a little bit
AllAmericanBreakfast · 2020-07-26T22:35:05.546Z · comments (3)
Developmental Stages of GPTs
orthonormal · 2020-07-26T22:03:19.588Z · comments (73)
You Can Probably Amplify GPT3 Directly
Zachary Robertson (zachary-robertson) · 2020-07-26T21:58:53.962Z · comments (14)
The problem of Pop Analogy
thesilvermen · 2020-07-26T21:44:43.066Z · comments (None)
next page (older posts) →