Generating Conversation: RLHF and LLM Evaluations with Nathan Lambert (Episode 6) Published 2023-09-06 Download video MP4 360p Download video MP4 720p Recommendations 49:47 “What's wrong with LLMs and what we should be building instead” - Tom Dietterich - #VSCF2023 07:05 This is What Limits Current LLMs 10:48 RLHF+CHATGPT: What you must know 25:28 Generating Conversation: Gorilla, An LLM for Massive APIs - Shishir Patil, Tianjun Zhang (Episode 7) 44:54 Max Tegmark | On superhuman AI, future architectures, and the meaning of human existence 15:22 How Intelligence Evolved | The Role of Simulation 36:54 Prof. Geoffrey Hinton - "Will digital intelligence replace biological intelligence?" Romanes Lecture 1:16:15 Stanford CS224N | 2023 | Lecture 10 - Prompting, Reinforcement Learning from Human Feedback 17:57 Generative AI in a Nutshell - how to survive and thrive in the age of AI 33:50 Evaluating LLM-based Applications 38:09 Generating Conversation: Building a Business in Generative AI - Vik Singh (Episode 10) 29:15 Generating Conversation: MemGPT, Memory Management for LLMs - Charles Packer (Episode 9) 59:48 [1hr Talk] Intro to Large Language Models 1:05:32 François Chollet - Creating Keras 3 54:29 CS 285: Eric Mitchell: Reinforcement Learning from Human Feedback: Algorithms & Applications 12:38 Reinforcement Learning from Human Feedback (RLHF) 1:16:53 Yann Lecun | Objective-Driven AI: Towards AI systems that can learn, remember, reason, and plan 39:15 Possible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital 44:20 LLMs in the Enterprise: Tips from Netflix, Nvidia, & Meta | TransformX 2022 17:35 Intro to LLMs (Generating Conversation, Episode 1) Similar videos 36:25 Direct Preference Optimization (DPO): Your Language Model is Secretly a Reward Model Explained 1:03:32 John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges 1:02:41 Are Aligned Language Models “Adversarially Aligned”? 18:04 InstructGPT -Training language models to follow instructions with human feedback - short review 1:00:43 RLHF(Reinforcement Learning from Human Feedback) and InstructGPT 1:22:35 ThursdAI - Jan 31, 2024 Code LLama, Bard is 2nd best LLM?!, new LLaVa is great at OCR & more AI More results