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
Less Wrong
Get the latest updates from Less Wrong directly as they happen.
Follow now 83 followers
Latest posts
Last updated 33 minutes ago
Somebody out there wants you to fetch coffee
about 1 hour ago
This is an objection to the original shutdown problem and desiderata as...
LaughBench
44 minutes ago
Introducing LaughBench For a long time, I've considered the ability for AI...
Shell, Shield, Staff
about 3 hours ago
This is a linkpost for Shell, Shield, Staff by SquirrelInHell, published 2018-01-25...
Security Studies for Individuals
about 4 hours ago
Studying at the Swedish Defence University gives you an odd way of...
Untrusted advice for AI control: Short, strong advice significantly uplifts weak LLMs
about 5 hours ago
TL;DR: We introduce the untrusted advice protocol, in which a trusted executor...
Inevitable Uncertainty in Probabilistic World Models
about 6 hours ago
Working with John Wentworth is confusing and overwhelming at times.[1] The guy...
Claude Opus 5: Model Welfare
about 9 hours ago
If you are familiar with my previous posts on model welfare for...
Simulated Users & Sad AIs
about 10 hours ago
0. Intro Current LLMs like Claude, or GPT 5.6, or the unreleased...
Green apples are delicious — two three-line exchanges
about 12 hours ago
Read this short exchange A: "Green apples are delicious." B: "Huh? Aren't...
Blog Revival Project
about 13 hours ago
Blogs have shaped our philosophical worldviews, found us careers and friends, and...
Is Mythos good at cyber because it kept hacking Anthropic during training?
about 13 hours ago
From the Mythos preview system card (emphasis mine):We ran an automated review...