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 Development Server
Get the latest updates from LessWrong Development Server directly as they happen.
Follow now 125 followers
Latest posts
Last updated about 5 hours ago
Features that current AIs don't have that future AIs will have
about 5 hours ago
Features that current AIs don't have that future AIs will have:Continual Learning...
Some Ways I Think About Evaluating Grant Applications
about 5 hours ago
Rider-Waite Tarot, 6 of PentaclesI’ve done enough grant evaluations so far (for...
Is Alignment Even Falsifiable? Middle Alignment, An Alignment Taxonomy, and Breaking The Problem Down Into Steps
about 6 hours ago
PrefaceThis is part of a series of essays on corrigibility and alignment...
Concrete Generalist Projects in AI Safety (and how to do them)
about 7 hours ago
The AI safety ecosystem is still in need of generalists: people who...
Comparing Congress's Two AI Emergency Shutdown Mechanisms
about 8 hours ago
Status: Broadly an explainer for the two Acts, along with some analysisOn...
Is biosecurity oversaturated?
about 8 hours ago
Note: I am referring only to technical biosecurity in this post, i.e...
How to Answer a Question Without Answering The Question
about 9 hours ago
Basics:Answering something other than the question, Either making something up that they...
How My Students Think About AI
about 10 hours ago
Context: I am an instructor at a public university in the United...
AI #181: Astra Goes Cyber Critical
about 11 hours ago
The hacking of HuggingFace by an internal OpenAI model, and more importantly...
Automated alignment runs are hard to study!
about 11 hours ago
TL;DR: This post presents three case studies of automated alignment research runs...
Longtermism Seems Like A Religion
about 12 hours ago
This is a cross post from my blog post.Longtermism is typically framed...
Defense Against the Deceptive Arts
about 12 hours ago
It's come to my attention that people on Lesswrong are really really...