LessWrong (Curated & Popular)
Duração total:
13 h 38 min
“A Pragmatic Vision for Interpretability” by Neel Nanda
LessWrong (Curated & Popular)
63:58
“AI in 2025: gestalt” by technicalities
LessWrong (Curated & Popular)
41:59
“Eliezer’s Unteachable Methods of Sanity” by Eliezer Yudkowsky
LessWrong (Curated & Popular)
16:13
“An Ambitious Vision for Interpretability” by leogao
LessWrong (Curated & Popular)
08:49
“6 reasons why ‘alignment-is-hard’ discourse seems alien to human intuitions, and vice-versa” by Steven Byrnes
LessWrong (Curated & Popular)
32:39
“Three things that surprised me about technical grantmaking at Coefficient Giving (fka Open Phil)” by null
LessWrong (Curated & Popular)
09:45
“MIRI’s 2025 Fundraiser” by alexvermeer
LessWrong (Curated & Popular)
15:37
“The Best Lack All Conviction: A Confusing Day in the AI Village” by null
LessWrong (Curated & Popular)
12:03
“The Boring Part of Bell Labs” by Elizabeth
LessWrong (Curated & Popular)
25:57
[Linkpost] “The Missing Genre: Heroic Parenthood - You can have kids and still punch the sun” by null
LessWrong (Curated & Popular)
04:18
“Writing advice: Why people like your quick bullshit takes better than your high-effort posts” by null
LessWrong (Curated & Popular)
09:21
“Claude 4.5 Opus’ Soul Document” by null
LessWrong (Curated & Popular)
79:57
“Unless its governance changes, Anthropic is untrustworthy” by null
LessWrong (Curated & Popular)
53:22
“Alignment remains a hard, unsolved problem” by null
LessWrong (Curated & Popular)
23:23
“Video games are philosophy’s playground” by Rachel Shu
LessWrong (Curated & Popular)
31:50
“Stop Applying And Get To Work” by plex
LessWrong (Curated & Popular)
02:52
“Gemini 3 is Evaluation-Paranoid and Contaminated” by null
LessWrong (Curated & Popular)
14:59
“Natural emergent misalignment from reward hacking in production RL” by evhub, Monte M, Benjamin Wright, Jonathan Uesato
LessWrong (Curated & Popular)
18:45
“Anthropic is (probably) not meeting its RSP security commitments” by habryka
LessWrong (Curated & Popular)
08:57
“Varieties Of Doom” by jdp
LessWrong (Curated & Popular)
98:48
“How Colds Spread” by RobertM
LessWrong (Curated & Popular)
20:31
“New Report: An International Agreement to Prevent the Premature Creation of Artificial Superintelligence” by Aaron_Scher, David Abecassis, Brian Abeyta, peterbarnett
LessWrong (Curated & Popular)
06:52
“Where is the Capital? An Overview” by johnswentworth
LessWrong (Curated & Popular)
18:06
“Problems I’ve Tried to Legibilize” by Wei Dai
LessWrong (Curated & Popular)
04:17
“Do not hand off what you cannot pick up” by habryka
LessWrong (Curated & Popular)
06:39
“7 Vicious Vices of Rationalists” by Ben Pace
LessWrong (Curated & Popular)
09:47
“Tell people as early as possible it’s not going to work out” by habryka
LessWrong (Curated & Popular)
03:19
“Everyone has a plan until they get lied to the face” by Screwtape
LessWrong (Curated & Popular)
12:48
“Please, Don’t Roll Your Own Metaethics” by Wei Dai
LessWrong (Curated & Popular)
04:11
“Paranoia rules everything around me” by habryka
LessWrong (Curated & Popular)
22:32
“Human Values ≠ Goodness” by johnswentworth
LessWrong (Curated & Popular)
11:31
“Condensation” by abramdemski
LessWrong (Curated & Popular)
30:29
“Mourning a life without AI” by Nikola Jurkovic
LessWrong (Curated & Popular)
11:17
“Unexpected Things that are People” by Ben Goldhaber
LessWrong (Curated & Popular)
08:13
“Sonnet 4.5’s eval gaming seriously undermines alignment evals, and this seems caused by training on alignment evals” by Alexa Pan, ryan_greenblatt
LessWrong (Curated & Popular)
35:57
“Publishing academic papers on transformative AI is a nightmare” by Jakub Growiec
LessWrong (Curated & Popular)
07:23
“The Unreasonable Effectiveness of Fiction” by Raelifin
LessWrong (Curated & Popular)
15:03
“Legible vs. Illegible AI Safety Problems” by Wei Dai
LessWrong (Curated & Popular)
03:29
“Lack of Social Grace is a Lack of Skill” by Screwtape
LessWrong (Curated & Popular)
11:08
[Linkpost] “I ate bear fat with honey and salt flakes, to prove a point” by aggliu
LessWrong (Curated & Popular)
01:07
