#7: Nora Belrose - EleutherAI, Interpretability, Linguistics, and ELK

https://is1-ssl.mzstatic.com/image/thumb/Podcasts116/v4/ce/e1/c6/cee1c6b1-766b-9137-2409-b41df5796394/mza_467482820930693497.jpg/600x600bb.jpg

Theo Jaffee Podcast

Theo Jaffee

21 episodes

6 days ago

Deep conversations with brilliant people.

Technology

RSS

All content for Theo Jaffee Podcast is the property of Theo Jaffee and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Deep conversations with brilliant people.

Technology

https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/38564113/38564113-1690595532312-56289e25064c6.jpg

#7: Nora Belrose - EleutherAI, Interpretability, Linguistics, and ELK

Theo Jaffee Podcast

2 hours 24 minutes

2 years ago

#7: Nora Belrose - EleutherAI, Interpretability, Linguistics, and ELK

Nora Belrose is the Head of Interpretability at EleutherAI, and a noted AI optimist.

Nora’s Twitter: https://x.com/norabelrose
EleutherAI Website: https://www.eleuther.ai/
EleutherAI Discord: https://discord.gg/zBGx3azzUn

PODCAST LINKS:

Video Transcript: https://www.theojaffee.com/p/7-nora-belrose
Spotify: https://open.spotify.com/show/1IJRtB8FP4Cnq8lWuuCdvW?si=eba62a72e6234efb
Apple Podcasts: https://podcasts.apple.com/us/podcast/theo-jaffee-podcast/id1699912677
RSS: https://api.substack.com/feed/podcast/989123/s/75569/private/129f6344-c459-4581-a9da-dc331677c2f6.rss
Playlist of all episodes: https://www.youtube.com/playlist?list=PLVN8-zhbMh9YnOGVRT9m0xzqTNGD_sujj
My Twitter: https://x.com/theojaffee
My Substack: https://www.theojaffee.com

CHAPTERS:

Intro (0:00)

EleutherAI (0:32)

Optimism (8:02)

Linguistics (22:27)

What Should AIs Do? (32:01)

Regulation (43:44)

Future Vibes (53:56)

Anthropic Polysemanticity (1:05:05)

More Interpretability (1:19:52)

Eliciting Latent Knowledge (1:44:44)