Gå frakoblet med Player FM -appen!
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
Manage episode 432190301 series 3524393
The paper analyzes AI safety benchmarks, revealing their correlation with general capabilities, and proposes a clearer framework for defining and measuring AI safety research goals.
https://arxiv.org/abs//2407.21792
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
--- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/support
1645 episoder
Manage episode 432190301 series 3524393
The paper analyzes AI safety benchmarks, revealing their correlation with general capabilities, and proposes a clearer framework for defining and measuring AI safety research goals.
https://arxiv.org/abs//2407.21792
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
--- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/support
1645 episoder
Усі епізоди
×Velkommen til Player FM!
Player FM scanner netter for høykvalitets podcaster som du kan nyte nå. Det er den beste podcastappen og fungerer på Android, iPhone og internett. Registrer deg for å synkronisere abonnement på flere enheter.