AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
15min chapter
Localizing and Editing Knowledge in LLMs with Peter Hase - #679
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Model Deletion and Defense Strategies Against Information Extraction
This chapter explores the necessity of deleting information from models through machine unlearning techniques. It delves into defending against white box attacks and fine-tuning models to restrict sensitive data responses. The conversation also delves into scalable oversight in training language models and analyzing question hardness for model generalization.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode