[Linkpost] “Pause House, Blackpool” by Greg C
13 Oct 2025
1m
LessWrong · Philosophy
LessWrong (30+ Karma)
Audio narrations of LessWrong posts.
Episodes
“The Narcissistic Spectrum” by Dawn Drescher
13 Oct 2025
42m
“Don’t Mock Yourself” by Algon
13 Oct 2025
4m
“Emil the Moose” by Martin Sustrik
11 Oct 2025
3m
“Experiments With Sonnet 4.5 Fiction” by Tomás B.
11 Oct 2025
11m
“The Most Common Bad Argument In These Parts” by J Bostock
11 Oct 2025
8m
“Iterated Development and Study of Schemers (IDSS)” by ryan_greenblatt
10 Oct 2025
14m
“Training fails to elicit subtle reasoning in current language models” by mishajw, Fabien Roger, Hoagy, gasteigerjo, Joe Benton, Vlad Mikulik
10 Oct 2025
7m
“‘Yes, and—’ Requires the Possibility of ‘No, Because—’” by Zack_M_Davis
10 Oct 2025
6m
“Stars are a rounding error” by Algon
10 Oct 2025
5m
“Training Qwen-1.5B with a CoT legibility penalty” by Fabien Roger
10 Oct 2025
10m
“At odds with the unavoidable meta-message” by Ruby
10 Oct 2025
7m
“Towards a Typology of Strange LLM Chains-of-Thought” by 1a3orn
09 Oct 2025
17m
“I take antidepressants. You’re welcome” by Elizabeth
09 Oct 2025
6m
“Realistic Reward Hacking Induces Different and Deeper Misalignment” by Jozdien
09 Oct 2025
21m
“The Thinking Machines Tinker API is good news for AI control and security” by Buck
09 Oct 2025
11m
“Hospitalization: A Review” by Logan Riggs
09 Oct 2025
18m
“The Relationship Between Social Punishment and Shared Maps” by Zack_M_Davis
09 Oct 2025
8m
“Spooky Collusion at a Distance with Superrational AI” by bira
09 Oct 2025
13m
“Inoculation prompting: Instructing models to misbehave at train-time can improve run-time behavior” by Sam Marks
08 Oct 2025
4m
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.