Published Sep 23, 2024
Stealing Weights of a Production LLM Like OpenAI’s ChatGPT with Nicholas Carlini - 702
Research scientist Nicholas Carlini delves into the vulnerabilities of AI models, highlighting his pioneering efforts in adversarial machine learning and the implications of model stealing on AI security, privacy, and ethical considerations, with insights into how companies are countering these threats.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - 678
Answers 383 questions
Privacy and Security for Stable Diffusion and LLMs with Nicholas Carlini - 618
Answers 383 questions
Watermarking LLMs to Fight Plagiarism with Tom Goldstein - 621
Answers 383 questions
Language Understanding and LLMs with Christopher Manning - 686
Answers 383 questions
BloombergGPT - an LLM for Finance with David Rosenberg - 639
Answers 383 questions
Are Large Language Models a Path to AGI? with Ben Goertzel - 625
Answers 383 questions
Natural Language Processing at StockTwits with Garrett Hoffman - TWiML Talk #194
Answers 383 questions
AI Agents and Data Integration with GPT and LLaMa with Jerry Liu - 628
Answers 383 questions
Deep Learning, Transformers, and the Consequences of Scale with Oriol Vinyals - #546
Answers 383 questions
Productive Machine Learning at LinkedIn with Bee-Chung Chen - TWiML Talk #200
Answers 383 questions
Ensuring LLM Safety for Production Applications with Shreya Rajpal - 647
Answers 383 questions
