How to Steal ChatGPT’s Embedding Size, and Other Low-rank Logit Tricks Published 2024-04-26 Download video MP4 360p Download video MP4 720p Recommendations 58:32 Informative Example Selection for In-Context Learning 19:56 “I worry that AI will be used to manipulate large groups of people” 56:00 The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI 1:01:31 Understanding LLMs through their Generative Behavior, Successes and Shortcomings 13:30 Big Idea t test v z test 13:02 We Were Wrong About Gold's Origin 59:24 Terry Tao, Ph.D. Small and Large Gaps Between the Primes 16:36 Nvidia's Breakthrough AI Chip Defies Reason! (COMPUTEX 2024 Supercut) 2:47:12 Confirmatory Factor Analysis in R with lavaan 47:51 Terence Tao: Structure and Randomness in the Prime Numbers, UCLA 50:26 Tom Goldstein: "What do neural loss surfaces look like?" 21:14 Starship Flight 4 Update // Giant Stars Disappearing // Volcanoes on Venus 13:03 Does Hollywood ruin books? - Numberphile 59:37 Causal Inference to Inform Curation Practices in Online Platforms 1:12:03 Steve Brunton: "Introduction to Fluid Mechanics" 51:49 Terence Tao: The Erdős Discrepancy Problem 19:51 “The talk around AI replacing us is the most misunderstood concept in AI” 19:42 "AIs will give you answers even if they don’t know" 56:16 Judea Pearl Tribute Symposium: Causality 50:06 Maziar Raissi: "Hidden Physics Models: Machine Learning of Non-Linear Partial Differential Equat..." Similar videos 00:46 3 ILLEGAL apps that are now BANNED ❌ 00:41 EXPOSING A ROBLOX HACKER ON DISCORD 04:29 How Easy Is It For Hackers To Brute Force Login Pages?! 3:57:44 Mechanistic Interpretability - NEEL NANDA (DeepMind) 1:00:23 LLMs for Classification Tasks with LLM Studio 53:56 Fine-tuning LLMs with Hugging Face SFT 🚀 | QLoRA | LLMOps 1:17:04 Stanford CS224N NLP with Deep Learning | 2023 | Lecture 8 - Self-Attention and Transformers 1:01:01 Mastering RLHF with AWS: A Hands-on Workshop on Reinforcement Learning from Human Feedback 3:13:13 Sholto Douglas & Trenton Bricken - How to Build & Understand GPT-7's Mind 1:49:36 ACM AI | Reading Group W24W5 | Mechanistic Interpretability: Understanding Transformer Circuits 1:21:28 [MLOpsVN] Seminar #13: GPT Prompt Engineering 1:11:02 Keynote - Security Issues in Generative AI 11:54:56 LIVE: ABC News Live - Monday, November 6 | ABC News More results