Artwork

Innhold levert av TWIML and Sam Charrington. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av TWIML and Sam Charrington eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.
Player FM - Podcast-app
Gå frakoblet med Player FM -appen!

Localizing and Editing Knowledge in LLMs with Peter Hase - #679

49:46
 
Del
 

Manage episode 411383461 series 2355587
Innhold levert av TWIML and Sam Charrington. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av TWIML and Sam Charrington eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.

Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models.

The complete show notes for this episode can be found at twimlai.com/go/679.

  continue reading

749 episoder

Artwork
iconDel
 
Manage episode 411383461 series 2355587
Innhold levert av TWIML and Sam Charrington. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av TWIML and Sam Charrington eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.

Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models.

The complete show notes for this episode can be found at twimlai.com/go/679.

  continue reading

749 episoder

Tất cả các tập

×
 
Loading …

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.

 

Hurtigreferanseguide

Copyright 2025 | Sitemap | Personvern | Vilkår for bruk | | opphavsrett
Lytt til dette showet mens du utforsker
Spill