LessWrong (Curated & Popular)ポッドキャストを聴こう

“Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety” by Tomek Korbak, Mikita Balesni, Vlad Mikulik, Rohin Shah	LessWrong (Curated & Popular)	02:15
“the jackpot age” by thiccythot	LessWrong (Curated & Popular)	12:39
“Surprises and learnings from almost two months of Leo Panickssery” by Nina Panickssery	LessWrong (Curated & Popular)	11:55
“An Opinionated Guide to Using Anki Correctly” by Luise	LessWrong (Curated & Popular)	54:12
“Lessons from the Iraq War about AI policy” by Buck	LessWrong (Curated & Popular)	07:58
“So You Think You’ve Awoken ChatGPT” by JustisMills	LessWrong (Curated & Popular)	17:58
“Generalized Hangriness: A Standard Rationalist Stance Toward Emotions” by johnswentworth	LessWrong (Curated & Popular)	12:26
“Comparing risk from internally-deployed AI to insider and outsider threats from humans” by Buck	LessWrong (Curated & Popular)	05:19
“Why Do Some Language Models Fake Alignment While Others Don’t?” by abhayesian, John Hughes, Alex Mallen, Jozdien, janus, Fabien Roger	LessWrong (Curated & Popular)	11:06
“A deep critique of AI 2027’s bad timeline models” by titotal	LessWrong (Curated & Popular)	72:32
“‘Buckle up bucko, this ain’t over till it’s over.’” by Raemon	LessWrong (Curated & Popular)	06:12
“Shutdown Resistance in Reasoning Models” by benwr, JeremySchlatter, Jeffrey Ladish	LessWrong (Curated & Popular)	18:01
“Authors Have a Responsibility to Communicate Clearly” by TurnTrout	LessWrong (Curated & Popular)	11:08
“The Industrial Explosion” by rosehadshar, Tom Davidson	LessWrong (Curated & Popular)	31:57
“Race and Gender Bias As An Example of Unfaithful Chain of Thought in the Wild” by Adam Karvonen, Sam Marks	LessWrong (Curated & Popular)	07:56
“The best simple argument for Pausing AI?” by Gary Marcus	LessWrong (Curated & Popular)	02:00
“Foom & Doom 2: Technical alignment is hard” by Steven Byrnes	LessWrong (Curated & Popular)	56:38
“Proposal for making credible commitments to AIs.” by Cleo Nardo	LessWrong (Curated & Popular)	05:19
“X explains Z% of the variance in Y” by Leon Lang	LessWrong (Curated & Popular)	18:52
“A case for courage, when speaking of AI danger” by So8res	LessWrong (Curated & Popular)	10:12
“My pitch for the AI Village” by Daniel Kokotajlo	LessWrong (Curated & Popular)	13:27
“Foom & Doom 1: ‘Brain in a box in a basement’” by Steven Byrnes	LessWrong (Curated & Popular)	58:46
“Futarchy’s fundamental flaw” by dynomight	LessWrong (Curated & Popular)	15:28
“Do Not Tile the Lightcone with Your Confused Ontology” by Jan_Kulveit	LessWrong (Curated & Popular)	11:28
“Endometriosis is an incredibly interesting disease” by Abhishaike Mahajan	LessWrong (Curated & Popular)	35:13
“Estrogen: A trip report” by cube_flipper	LessWrong (Curated & Popular)	50:49
“New Endorsements for ‘If Anyone Builds It, Everyone Dies’” by Malo	LessWrong (Curated & Popular)	08:55
[Linkpost] “the void” by nostalgebraist	LessWrong (Curated & Popular)	01:14
“Mech interp is not pre-paradigmatic” by Lee Sharkey	LessWrong (Curated & Popular)	29:33
“Distillation Robustifies Unlearning” by Bruce W. Lee, Addie Foote, alexinf, leni, Jacob G-W, Harish Kamath, Bryce Woodworth, cloud, TurnTrout	LessWrong (Curated & Popular)	17:19
“Intelligence Is Not Magic, But Your Threshold For ‘Magic’ Is Pretty Low” by Expertium	LessWrong (Curated & Popular)	03:12
“A Straightforward Explanation of the Good Regulator Theorem” by Alfred Harwood	LessWrong (Curated & Popular)	29:24
“Beware General Claims about ‘Generalizable Reasoning Capabilities’ (of Modern AI Systems)” by LawrenceC	LessWrong (Curated & Popular)	34:11
“Season Recap of the Village: Agents raise $2,000” by Shoshannah Tekofsky	LessWrong (Curated & Popular)	13:24
“The Best Reference Works for Every Subject” by Parker Conley	LessWrong (Curated & Popular)	13:02
“‘Flaky breakthroughs’ pervade coaching — and no one tracks them” by Chipmonk	LessWrong (Curated & Popular)	09:31
“The Value Proposition of Romantic Relationships” by johnswentworth	LessWrong (Curated & Popular)	23:19
“It’s hard to make scheming evals look realistic” by Igor Ivanov, dan_moken	LessWrong (Curated & Popular)	07:47
[Linkpost] “Social Anxiety Isn’t About Being Liked” by Chipmonk	LessWrong (Curated & Popular)	05:23
“Truth or Dare” by Duncan Sabien (Inactive)	LessWrong (Curated & Popular)	123:21

“Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety” by Tomek Korbak, Mikita Balesni, Vlad Mikulik, Rohin Shah

LessWrong (Curated & Popular)

02:15

“the jackpot age” by thiccythot

LessWrong (Curated & Popular)

12:39

“Surprises and learnings from almost two months of Leo Panickssery” by Nina Panickssery

LessWrong (Curated & Popular)

11:55

“An Opinionated Guide to Using Anki Correctly” by Luise

LessWrong (Curated & Popular)

54:12