Troy Tian — LessWrong

My reactions to “I underestimated AI capabilities (again)”

An application response I wrote! Please feel free to leave any feedback! Describe a recent paper or blog post that has influenced your perspective on AI safety. “I underestimated AI capabilities (again)” (https://www.planned-obsolescence.org/p/i-underestimated-ai-capabilities) came out at the beginning of March. In one sentence, author Ajeya Cotra made capabilities predictions in...

Jun 13

Why I think evals are pretty important and most worth working on (for me)

An application response I wrote! Feel free to leave feedback! What are you most concerned about when it comes to risks from AI? I’m most concerned that many people will be harmed very soon, and particularly that we won’t know why. Since politics and government dictate public life, solving said...

May 317

Troy Tian's Shortform

May 311