Artwork

Konten disediakan oleh TWIML and Sam Charrington. Semua konten podcast termasuk episode, grafik, dan deskripsi podcast diunggah dan disediakan langsung oleh TWIML and Sam Charrington atau mitra platform podcast mereka. Jika Anda yakin seseorang menggunakan karya berhak cipta Anda tanpa izin, Anda dapat mengikuti proses yang diuraikan di sini https://id.player.fm/legal.
Player FM - Aplikasi Podcast
Offline dengan aplikasi Player FM !

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

49:46
 
Bagikan
 

Manage episode 411383461 series 2355587
Konten disediakan oleh TWIML and Sam Charrington. Semua konten podcast termasuk episode, grafik, dan deskripsi podcast diunggah dan disediakan langsung oleh TWIML and Sam Charrington atau mitra platform podcast mereka. Jika Anda yakin seseorang menggunakan karya berhak cipta Anda tanpa izin, Anda dapat mengikuti proses yang diuraikan di sini https://id.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

726 episode

Artwork
iconBagikan
 
Manage episode 411383461 series 2355587
Konten disediakan oleh TWIML and Sam Charrington. Semua konten podcast termasuk episode, grafik, dan deskripsi podcast diunggah dan disediakan langsung oleh TWIML and Sam Charrington atau mitra platform podcast mereka. Jika Anda yakin seseorang menggunakan karya berhak cipta Anda tanpa izin, Anda dapat mengikuti proses yang diuraikan di sini https://id.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

726 episode

Semua episode

×
 
Loading …

Selamat datang di Player FM!

Player FM memindai web untuk mencari podcast berkualitas tinggi untuk Anda nikmati saat ini. Ini adalah aplikasi podcast terbaik dan bekerja untuk Android, iPhone, dan web. Daftar untuk menyinkronkan langganan di seluruh perangkat.

 

Panduan Referensi Cepat