Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feederlesswrong.com
LessWrong
Get the latest updates from LessWrong directly as they happen.
Follow now 110 followers
Latest posts
Last updated 2 minutes ago
Insights into Claude Opus 4.5 from Pokémon
18 minutes ago
Published on December 9, 2025 4:57 PM GMTCredit: Nano Banana, with some...
The behavioral selection model for predicting AI motivations
4 days ago
Published on December 4, 2025 6:46 PM GMTHighly capable AI systems might...
The Most Common Bad Argument In These Parts
8 days ago
Published on October 11, 2025 4:29 PM GMTI've noticed an antipattern. It's...
Alignment remains a hard, unsolved problem
11 days ago
Published on November 27, 2025 8:45 AM GMTThis is a public adaptation...
Why people like your quick bullshit takes better than your high-effort posts
15 days ago
Published on November 28, 2025 8:12 PM GMTRight now I’m coaching for...
Natural emergent misalignment from reward hacking in production RL
19 days ago
Published on November 21, 2025 8:00 PM GMTAbstractWe show that when large...
How Colds Spread
23 days ago
Published on November 18, 2025 5:25 AM GMTIt seems like a catastrophic...
The Memetics of AI Successionism
26 days ago
Published on October 28, 2025 3:04 PM GMTTL;DR: AI progress and the...
Paranoia: A Beginner's Guide
about 1 month ago
Published on November 13, 2025 7:56 AM GMTPeople sometimes make mistakes. (Citation...
Human Values ≠ Goodness
about 1 month ago
Published on November 2, 2025 7:24 PM GMTThere is a temptation to...
Legible vs. Illegible AI Safety Problems
about 1 month ago
Published on November 4, 2025 9:39 PM GMTSome AI safety problems are...
The Unreasonable Effectiveness of Fiction
about 1 month ago
Published on November 3, 2025 3:35 PM GMT[Meta: This is Max Harms...