Published Apr 8, 2024
Localizing and Editing Knowledge in LLMs with Peter Hase - 679
Peter Hase delves into the challenges of localizing and editing knowledge in large language models, discussing sensitive information management, interpretability using causal tracing, and enhancing AI operations through easy-to-hard generalization and scalable oversight.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Language Understanding and LLMs with Christopher Manning - 686
Answers 383 questions
Reasoning Over Complex Documents with DocLLM with Armineh Nourbakhsh - 672
Answers 383 questions
The Enterprise LLM Landscape with Atul Deo - 640
Answers 383 questions
Building Real-World LLM Products with Fine-Tuning and More with Hamel Husain - 694
Answers 383 questions
Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - 678
Answers 383 questionsAre LLMs Good at Causal Reasoning? with Robert Osazuwa Ness - 638
Answers 383 questions
Building LLM-Based Applications with Azure OpenAI with Jay Emery - 657
Answers 383 questions
AI for High-Stakes Decision Making with Hima Lakkaraju - #387
Answers 383 questions
LSTMs, Plus a Deep Learning History Lesson with Jürgen Schmidhuber - #44
Answers 383 questions
Stable Diffusion and LLMs at the Edge with Jilei Hou - 633
Answers 383 questions
