Towards Reliable Use of Large Language Models: Better Detection, Consistency, and Instruction-Tuning Published 2023-08-14 Download video MP4 360p Recommendations 1:00:56 Are LLMs the Beginning or End of NLP? 57:21 An observation on Generalization 55:41 Language Understanding and LLMs with Christopher Manning - 686 56:25 The Unreasonable Effectiveness of Spectral Graph Theory: A Confluence of Algorithms, Geometry & ... 59:40 Integrating Language into Intelligent Architectures 1:27:56 Artificial Stupidity: The New AI and the Future of Fintech 49:47 “What's wrong with LLMs and what we should be building instead” - Tom Dietterich - #VSCF2023 54:49 Algorithmic Trading and Machine Learning 39:15 Possible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital 58:07 Aligning LLMs with Direct Preference Optimization 1:08:14 Cryptography: From Mathematical Magic to Secure Communication 28:18 Fine-tuning Large Language Models (LLMs) | w/ Example Code 45:32 A Survey of Techniques for Maximizing LLM Performance 26:55 ChatGPT: 30 Year History | How AI Learned to Talk 1:37:37 The Turing Lectures: The future of generative AI 51:32 Predictive Coding Models of Perception 55:55 Miles Cranmer - The Next Great Scientific Theory is Hiding Inside a Neural Network (April 3, 2024) 27:14 But what is a GPT? Visual intro to Transformers | Chapter 5, Deep Learning Similar videos 00:59 What are large language models? #llm #ai #machinelearning 1:18:36 Instruction finetuning and RLHF lecture (NYU CSCI 2590) 09:10 Direct Preference Optimization: Forget RLHF (PPO) 06:26 Large Language Models and BERT - Chris Manning Stanford CoreNLP 36:25 Direct Preference Optimization (DPO): Your Language Model is Secretly a Reward Model Explained 01:48 Chomsky vs Shannon approaches to NLP and AI - Chris Manning Stanford OpenNLP creator 09:41 Future of NLP - Chris Manning Stanford CoreNLP 05:38 Self-Consistency Improves Chain of Thought Reasoning in Language Models 1:41:03 How large language models work (and why that's why they don't) 1:15:04 Watermarking of Large Language Models More results