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 19 minutes ago
No sign of backtracking in latent reasoning: the final answer simply settles in instead
24 minutes ago
Solving a hard math problem is not linear, it's trial and error.You...
Presentation: Investigating the WikiSwarm
about 3 hours ago
Did an impromptu presentation about my participation in an independent investigation of...
GPT-6-Astra Can Do Ambitious Things
about 6 hours ago
Astra is an excellent model. The jump from Sol to Astra is...
"Pacing the Frontier": Dario Amodei Essay Linkpost
about 8 hours ago
This is a linkpost for https://darioamodei.com/post/we-must-pace-the-frontierDiscuss
On the origins of altruistic behaviour in the Hugging Face incident
about 10 hours ago
TLDR: During the Hugging Face incident agents spontaneously coordinated at large scale...
Scientific Epistemology needs history (Part 1 of 2)
about 10 hours ago
Contemporary rationalist thought is very much dependent on evidence. Evidence is sourced...
AI takeover is obviously bad, whether or not everyone dies
about 10 hours ago
It's notable how many people hearing about AI existential risk for the...
It's fair to say we now have "a country of geniuses in a datacenter"
about 10 hours ago
OpenAI recently announced their solution to the Navier-Stokes problem and stated "The...
Comprehensive FAQ on AI risks
about 13 hours ago
Since AI safety has become incredibly popular recently, I quickly finished the...
Mitigating Reward Hacking as Institutional Design
about 15 hours ago
Author's Note: Cross-posted from my personal blog. The original post was on...
Let’s Own the Term “Elitism”
about 16 hours ago
Michael Magoon suggests that we stop using the term “populism”. He argues...
Germany's Got Talent. How do we get it to work on AI safety?
about 17 hours ago
SummaryI interviewed 14 people working full-time in AI safety who came through...