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

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

Author: Sam Charrington April 9, 2024 Duration: 49:46
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.

Hosted by industry analyst and commentator Sam Charrington, The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) serves as a vital conduit between cutting-edge research and its real-world implications. This isn't just a series of technical lectures; it's a series of conversations that unpack how AI and machine learning are actively reshaping industries and societal structures. Each episode connects you directly with leading researchers, engineers, and innovative thinkers who are defining the frontiers of the field. The discussions go beyond abstract theory to explore the practical challenges, ethical considerations, and business transformations driven by these technologies. Whether you're a data scientist deep in the code, a tech-savvy leader strategizing implementation, or simply fascinated by the future of intelligent systems, this podcast provides the context and depth needed to stay informed. By focusing on the people behind the algorithms and the ideas powering the platforms, Sam creates a resource that is both intellectually substantive and genuinely engaging, building a thoughtful community around one of the most significant technological shifts of our time.
Author: Language: English Episodes: 100

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Podcast Episodes
ML Models for Safety-Critical Systems with Lucas García - #705 [not-audio_url] [/not-audio_url]

Duration: 1:16:06
Today, we're joined by Lucas García, principal product manager for deep learning at MathWorks to discuss incorporating ML models into safety-critical systems. We begin by exploring the critical role of verification and v…
AI Agents: Substance or Snake Oil with Arvind Narayanan - #704 [not-audio_url] [/not-audio_url]

Duration: 54:22
Today, we're joined by Arvind Narayanan, professor of Computer Science at Princeton University to discuss his recent works, AI Agents That Matter and AI Snake Oil. In “AI Agents That Matter”, we explore the range of agen…
AI Agents for Data Analysis with Shreya Shankar - #703 [not-audio_url] [/not-audio_url]

Duration: 48:24
Today, we're joined by Shreya Shankar, a PhD student at UC Berkeley to discuss DocETL, a declarative system for building and optimizing LLM-powered data processing pipelines for large-scale and complex document analysis…
Automated Design of Agentic Systems with Shengran Hu - #700 [not-audio_url] [/not-audio_url]

Duration: 59:30
Today, we're joined by Shengran Hu, a PhD student at the University of British Columbia, to discuss Automated Design of Agentic Systems (ADAS), an approach focused on automatically creating agentic system designs. We exp…
The Building Blocks of Agentic Systems with Harrison Chase - #698 [not-audio_url] [/not-audio_url]

Duration: 59:17
Today, we're joined by Harrison Chase, co-founder and CEO of LangChain to discuss LLM frameworks, agentic systems, RAG, evaluation, and more. We dig into the elements of a modern LLM framework, including the most product…
Genie: Generative Interactive Environments with Ashley Edwards - #696 [not-audio_url] [/not-audio_url]

Duration: 46:51
Today, we're joined by Ashley Edwards, a member of technical staff at Runway, to discuss Genie: Generative Interactive Environments, a system for creating ‘playable’ video environments for training deep reinforcement lea…