“LLMs struggle to verbalize their internal reasoning” by Emil Ryd
15 Feb 2026
19m
LessWrong · Philosophy
LessWrong (30+ Karma)
Audio narrations of LessWrong posts.
Episodes
“ChatGPT-5.3-Codex Is Also Good At Coding” by Zvi
15 Feb 2026
42m
“Hazards of Selection Effects on Approved Information” by Zack_M_Davis
14 Feb 2026
21m
“A multi-level postmortem of how our whole house got badly poisoned” by Lucie Philippon
14 Feb 2026
12m
“Why I’m Worried About Job Loss + Thoughts on Comparative Advantage” by claywren
14 Feb 2026
21m
“Life at the Frontlines of Demographic Collapse” by Martin Sustrik
14 Feb 2026
17m
“Paper: Prompt Optimization Makes Misalignment Legible” by Caleb Biddulph, micahcarroll
14 Feb 2026
16m
“Why You Don’t Believe in Xhosa Prophecies” by Jan_Kulveit
13 Feb 2026
9m
“Gemini’s Hypothetical Present” by jefftk
13 Feb 2026
4m
“Human-like metacognitive skills will reduce LLM slop and aid alignment and capabilities” by Seth Herd
13 Feb 2026
35m
“Optimal Timing for Superintelligence: Mundane Considerations for Existing People” by Nick Bostrom
12 Feb 2026
1h 23m
“The Facade of AI Safety Will Crumble” by Liron
12 Feb 2026
7m
“Claude Opus 4.6 Escalates Things Quickly” by Zvi
12 Feb 2026
1h 14m
“Research note: A simpler AI timelines model predicts 99% AI R&D automation in ~2032” by Thomas Kwa
12 Feb 2026
20m
“Distinguish between inference scaling and “larger tasks use more compute”” by ryan_greenblatt
11 Feb 2026
5m
“Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning” by Wuschel Schulz
11 Feb 2026
11m
“Claude Opus 4.6: System Card Part 1: Mundane Alignment and Model Welfare” by Zvi
11 Feb 2026
55m
“Designing Prediction Markets” by ToasterLightning
11 Feb 2026
16m
“LLMs Views on Philosophy 2026” by JonathanErhardt
11 Feb 2026
2m
[Linkpost] “LessOnline 2026: June 5-7, Berkeley, CA (save the date)” by Ruby
11 Feb 2026
1m
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.