“Human Values ≠ Goodness” by johnswentworth
02 Nov 2025
11m
LessWrong · Philosophy
LessWrong (30+ Karma)
Audio narrations of LessWrong posts.
Episodes
“Reflections on 4 years of meta-honesty” by GradientDissenter
02 Nov 2025
11m
[Linkpost] “FTL travel and scientific realism” by Adam Scherlis
02 Nov 2025
0m
“Why Is Printing So Bad?” by johnswentworth
02 Nov 2025
3m
[Linkpost] “You’re always stressed, your mind is always busy, you never have enough time” by mingyuan
02 Nov 2025
4m
“Post title: Why I Transitioned: A Case Study” by Fiora Sunshine
02 Nov 2025
17m
“Re-rolling environment” by Raemon
01 Nov 2025
2m
“LLM-generated text is not testimony” by TsviBT
01 Nov 2025
19m
“Supervillain Monologues Are Unrealistic” by Algon
01 Nov 2025
4m
“Anthropic’s Pilot Sabotage Risk Report” by dmz
01 Nov 2025
6m
“OpenAI Moves To Complete Potentially The Largest Theft In Human History” by Zvi
31 Oct 2025
37m
“Resampling Conserves Redundancy & Mediation (Approximately) Under the Jensen-Shannon Divergence” by David Lorell
31 Oct 2025
9m
“Steering Evaluation-Aware Models to Act Like They Are Deployed” by Tim Hua, andrq, Sam Marks, Neel Nanda
30 Oct 2025
30m
[Linkpost] “AISLE discovered three new OpenSSL vulnerabilities” by Jan_Kulveit
30 Oct 2025
2m
“Sonnet 4.5’s eval gaming seriously undermines alignment evals, and this seems caused by training on alignment evals” by Alexa Pan, ryan_greenblatt
30 Oct 2025
35m
“ImpossibleBench: Measuring Reward Hacking in LLM Coding Agents” by Ziqian Zhong
30 Oct 2025
8m
[Linkpost] “Emergent Introspective Awareness in Large Language Models” by Drake Thomas
30 Oct 2025
3m
“An Opinionated Guide to Privacy Despite Authoritarianism” by TurnTrout
29 Oct 2025
8m
“The End of OpenAI’s Nonprofit Era” by garrison
29 Oct 2025
17m
“Please Do Not Sell B30A Chips to China” by Zvi
29 Oct 2025
13m
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.