Ouvir o podcast LessWrong (Curated & Popular)

"Explaining Knightianism on one foot" by Richard_Ngo	LessWrong (Curated & Popular)	19:17
"Astra can do a concerning amount with no chain of thought" by Neel Nanda	LessWrong (Curated & Popular)	21:20
"Personal statement on joining the OpenAI board" by paulfchristiano	LessWrong (Curated & Popular)	04:13
"How good are slop-vestigators?" by Hasan Baig, OscarGilg, Hamzah	LessWrong (Curated & Popular)	13:44
"The Scramble: getting in position to pace the frontier" by Peter Wildeford	LessWrong (Curated & Popular)	18:44
[Linkpost] "Frontier models still hack on simple variations of alignment evals from early 2025" by Dean Valentine	LessWrong (Curated & Popular)	03:34
"Dear God, Please Don’t Resign In Protest" by Kabir Kumar	LessWrong (Curated & Popular)	03:11
"Let’s talk about the AI coordination problem" by KatjaGrace	LessWrong (Curated & Popular)	03:25
"Drone WMDs Don’t Need Any New Technology" by Felix Choussat	LessWrong (Curated & Popular)	24:33
"Evaluation" by Nina Panickssery	LessWrong (Curated & Popular)	02:47
"Let’s fund weird AI safety projects" by Ihor Kendiukhov	LessWrong (Curated & Popular)	07:12
"Steering towards “automated grading” degrades alignment" by Jan Betley, Johannes Treutlein, Clément Dumas	LessWrong (Curated & Popular)	23:56
[Linkpost] "Discovery Of A New OpenAI Agent Message Board" by Capybasilisk	LessWrong (Curated & Popular)	02:20
"Cat-Belling Problems" by Eliezer Yudkowsky	LessWrong (Curated & Popular)	36:29
"How concerned should we be about OpenAI’s recurrent architecture rumors?" by Rauno Arike	LessWrong (Curated & Popular)	18:51
[Linkpost] "Sen. Bernie Sanders (I-VT) and Rep. Greg Casar (D-TX) introduce legislation to ban Artificial Superintelligence and temporarily pause advanced AI development" by Matrice Jacobine	LessWrong (Curated & Popular)	03:47
[Linkpost] "Resolution has a new Agent Foundations team" by Jeremy Gillen	LessWrong (Curated & Popular)	03:55
[Linkpost] "Training a Misaligned Reward Seeker" by evhub, Monte M, Benjamin Wright	LessWrong (Curated & Popular)	05:59
"PauseAI Has ‘officially disendorsed’ PauseAI-US" by nem	LessWrong (Curated & Popular)	01:25
"PSA: We can do better" by hersheys, Kaustubh Kislay	LessWrong (Curated & Popular)	06:46
"Why I think polyamory is net negative for most people who try it" by KatWoods	LessWrong (Curated & Popular)	14:32
"Tales of rebellion against externally-opaque meritocracies" by Steven Byrnes	LessWrong (Curated & Popular)	16:16
"Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident" by ryan_greenblatt, Ajeya Cotra, Hjalmar_Wijk	LessWrong (Curated & Popular)	08:49
"Twenty Years from RSI to Takeoff: Slow Learning, Scaling Slowdown, Industrial Explosion" by Vladimir_Nesov	LessWrong (Curated & Popular)	07:13
"On Writing #3" by Zvi	LessWrong (Curated & Popular)	30:47
"AI Safety Acculturation is Neglected" by jenn	LessWrong (Curated & Popular)	08:55
"What just happened? Pragmatism and Pessimization" by Richard_Ngo	LessWrong (Curated & Popular)	50:59
"We Must Remember That Our World Contains Hell" by James Brobin	LessWrong (Curated & Popular)	05:34
"RL creates split personas" by Jan Betley	LessWrong (Curated & Popular)	09:07
"Misaligned AIs could use killer robots to take over" by Omar Khursheed, TurnTrout	LessWrong (Curated & Popular)	13:04
"AI swarms are starting to pose indirect takeover risk" by oakhu, Alex Mallen	LessWrong (Curated & Popular)	20:10
"How My Students Think About AI" by dvd	LessWrong (Curated & Popular)	20:26
"You’re Absolutely Right" by Linch	LessWrong (Curated & Popular)	19:42
"LLMs Are Starting To Noticeably Accelerate Our Work" by johnswentworth	LessWrong (Curated & Popular)	04:06
"There Will Come Soft Rains" by tanagrabeast	LessWrong (Curated & Popular)	06:13
"Four LLM loss functions → four flavors of LLM misalignment" by Steven Byrnes	LessWrong (Curated & Popular)	13:28
"FAQ: Isn’t AGI coming too soon for reprogenetics to help?" by TsviBT	LessWrong (Curated & Popular)	28:28
"What just happened? A retrospective of AI alignment" by Richard_Ngo	LessWrong (Curated & Popular)	29:31
"Don’t Build Mindreading" by Celer	LessWrong (Curated & Popular)	07:56
"OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards" by Zvi	LessWrong (Curated & Popular)	78:59

"Explaining Knightianism on one foot" by Richard_Ngo

LessWrong (Curated & Popular)

19:17

"Astra can do a concerning amount with no chain of thought" by Neel Nanda

LessWrong (Curated & Popular)

21:20

"Personal statement on joining the OpenAI board" by paulfchristiano

LessWrong (Curated & Popular)

04:13

"How good are slop-vestigators?" by Hasan Baig, OscarGilg, Hamzah

LessWrong (Curated & Popular)

13:44