upcarta
  • Sign In
  • Sign Up
  • Explore
  • Search

Owain Evans

owainevans.github.io
1 Follower
community-curated profile

Research Associate @fhioxford, Oxford University. AI Safety, Machine Learning. Prefer email to DM.

Overview Posts Content Recommendations
Featured content
See All
  • Teaching Models to Express Their Uncertainty in Words
    by Owain Evans
Recent recommendations
See All
  • #150 – Tom Davidson on how quickly AI could transform the world
    by Robert Wiblin
  • AXRP - the AI X-risk Research Podcast - 21 - Interpretability for Engineers with Stephen Casper
Recent posts
See All
Owain Evans @OwainEvans_UK · May 8, 2023
  • From Twitter

Excellent interview with Tom Davidson on formal models of AI take off speed. I'd be very excited to see people in AI and economics (or any other related discipline) critique and build on Tom's research.
Podcast episode May 5, 2023
#150 – Tom Davidson on how quickly AI could transform the world
by Robert Wiblin and Tom Davidson
Post Add to Collection Mark as Completed
Recommended by 1 person
1 mention
Share on Twitter Repost
Owain Evans @OwainEvans_UK · May 8, 2023
  • From Twitter

Good interview with Stephen Casper on interpretability and backdoor trojans:
Podcast episode May 2, 2023
AXRP - the AI X-risk Research Podcast - 21 - Interpretability for Engineers with Stephen Casper
Post Add to Collection Mark as Completed
Recommended by 1 person
1 mention
Share on Twitter Repost
  • upcarta ©2024
  • Home
  • About
  • Terms
  • Privacy
  • Cookies
  • @upcarta