Standford U on AI

During a recent Stanford Online webinar, “Making Gen AI Useful,” Aditya Challapally (ML Engineer at Microsoft) moderated an insightful conversation with Michelle Pokrass (Post-Training Research Lead at OpenAI) and Stanford professor Chris Potts. Together, they broke down how foundation models are refined after training, explored where emerging API capabilities are opening new doors for developers, and addressed what separates successful GenAI apps from those that fall short. Watch the full webinar: https://youtu.be/9-eXLFvAoKM?si=T6_... Learn more about Stanford Online's Generative AI Program: https://online.stanford.edu/program...

Learn more about Stanford's Healthcare AI programs: https://online.stanford.edu/artific... Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Hosts: Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Seth Hain, Senior Vice President of R&D, Epic In this episode, hosts Matt Lundgren and Justin Norton, and special guest Seth Hain, Senior Vice President of R&D at Epic explore the latest advancements in AI models, including #GPT5, and their impact on healthcare. The trio discuss the challenges of benchmarking AI in medicine, the integration of #AI into clinical workflows, and the development of specialized models like Cosmos for predictive healthcare. They also addresses the implications of AI-driven deskilling, the evolving relationship between human expertise and AI, and the future of user experience in healthcare technology. Whether you're a clinician, developer, or healthcare leader, this session offers valuable insights into the opportunities and challenges at the intersection of AI and healthcare. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education.

During a recent Stanford Online webinar, “Making Gen AI Useful,” Aditya Challapally (ML Engineer at Microsoft) moderated an insightful conversation with Michelle Pokrass (Post-Training Research Lead at OpenAI) and Stanford professor Chris Potts. Together, they broke down how foundation models are refined after training, explored where emerging API capabilities are opening new doors for developers, and addressed what separates successful GenAI apps from those that fall short. Watch the full webinar: https://youtu.be/9-eXLFvAoKM?si=T6_... Learn more about Stanford Online's Generative AI Program: https://online.stanford.edu/program...

During a recent Stanford Online webinar, “Making Gen AI Useful,” Aditya Challapally (ML Engineer at Microsoft) moderated an insightful conversation with Michelle Pokrass (Post-Training Research Lead at OpenAI) and Stanford professor Chris Potts. Together, they broke down how foundation models are refined after training, explored where emerging API capabilities are opening new doors for developers, and addressed what separates successful GenAI apps from those that fall short. Watch the full webinar: https://youtu.be/9-eXLFvAoKM?si=T6_... Learn more about Stanford Online's Generative AI Program: https://online.stanford.edu/program...

During a recent Stanford Online webinar, “Making Gen AI Useful,” Aditya Challapally (ML Engineer at Microsoft) moderated an insightful conversation with Michelle Pokrass (Post-Training Research Lead at OpenAI) and Stanford professor Chris Potts. Together, they broke down how foundation models are refined after training, explored where emerging API capabilities are opening new doors for developers, and addressed what separates successful GenAI apps from those that fall short. Watch the full webinar: https://youtu.be/9-eXLFvAoKM?si=T6_... Learn more about Stanford Online's Generative AI Program: https://online.stanford.edu/program...

During a recent Stanford Online webinar, “Making Gen AI Useful,” Aditya Challapally (ML Engineer at Microsoft) moderated an insightful conversation with Michelle Pokrass (Post-Training Research Lead at OpenAI) and Stanford professor Chris Potts. Together, they broke down how foundation models are refined after training, explored where emerging API capabilities are opening new doors for developers, and addressed what separates successful GenAI apps from those that fall short. Watch the full webinar: https://youtu.be/9-eXLFvAoKM?si=T6_... Learn more about Stanford Online's Generative AI Program: https://online.stanford.edu/program...

During a recent Stanford Online webinar, “Making Gen AI Useful,” Aditya Challapally (ML Engineer at Microsoft) moderated an insightful conversation with Michelle Pokrass (Post-Training Research Lead at OpenAI) and Stanford professor Chris Potts. Together, they broke down how foundation models are refined after training, explored where emerging API capabilities are opening new doors for developers, and addressed what separates successful GenAI apps from those that fall short. Watch the full webinar: https://youtu.be/9-eXLFvAoKM?si=T6_... Learn more about Stanford Online's Generative AI Program: https://online.stanford.edu/program...

Drs. Kristin Sainani and Regina Nuzzo explore innovative ways generative AI is reshaping their work in clinical research and epidemiology. This engaging session reveals how they leverage this powerful AI tool for tasks such as data analysis, decoding statistical analyses sections, and writing faster through AI-refined dictation. You'll also learn how Dr. Sainani and Dr. Nuzzo use generative AI in their daily lives—from homework help to motivational cartoons. Additionally, they discuss the limitations of large language models in statistical reasoning and what these shortcomings teach us about our understanding of data and research methodologies. Watch this insightful discussion at the critical intersection of AI and healthcare! Browse online health & medicine programs: https://online.stanford.edu/explore...

Hear more about Beiliei Zhu's experience taking courses in our AI Professional Program. You can learn more about the program here: https://online.stanford.edu/program... The Artificial Intelligence Professional Program will equip you with knowledge of the principles, tools, techniques, and technologies driving this transformation.This online program provides rigorous coverage of the most important topics in modern artificial intelligence, including: Machine Learning Deep Learning Natural Language Processing and Understanding Supervised and Unsupervised Learning Reinforcement Learning Graph Neural Networks (GNNs) Multi-Task and Meta-Learning

Hear more about Kuniaki Iwanami's experience taking courses in our AI Professional Program. You can learn more about the program here: https://online.stanford.edu/program... The Artificial Intelligence Professional Program will equip you with knowledge of the principles, tools, techniques, and technologies driving this transformation.This online program provides rigorous coverage of the most important topics in modern artificial intelligence, including: Machine Learning Deep Learning Natural Language Processing and Understanding Supervised and Unsupervised Learning Reinforcement Learning Graph Neural Networks (GNNs) Multi-Task and Meta-Learning

October 30, 2024 Joseph Jay Williams, University of Toronto Learn more about the speaker: https://www.psych.utoronto.ca/peopl... This lecture is from Stanford CS329H: Machine Learning from Human Preferences Machine learning from human preferences investigates mechanisms for capturing human and societal preferences and values in artificial intelligence (AI) systems and applications, e.g., for socio-technical applications such as algorithmic fairness and many language and robotics tasks when reward functions are otherwise challenging to specify quantitatively. While learning from human preferences has emerged as an increasingly important component of modern AI, e.g., credited with advancing the state of the art in language modeling and reinforcement learning, existing approaches are largely reinvented independently in each subfield, with limited connections drawn among them. This course will cover the foundations of learning from human preferences from first principles and outline connections to the growing literature on the topic. This includes but is not limited to: -Inverse reinforcement learning, which uses human preferences to specify the reinforcement learning reward function -Metric elicitation, which uses human preferences to specify tradeoffs for cost-sensitive classification -Reinforcement learning from human feedback, where human preferences are used to align a pre-trained language model View the course website: https://web.stanford.edu/class/cs32... Enroll in the course: https://online.stanford.edu/courses...

Learn more about Stanford's online Healthcare AI programs: https://online.stanford.edu/artific... Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Dr. Graham Walker, Co-Director of Advanced Development at Kaiser Permanente In the second episode of the Stanford AI in Medicine podcast, hosts Justin Norden and Matthew Lungren, along with guest Dr. Graham Walker, Co-Director of Advanced Development at Kaiser, discuss the latest developments in AI models, particularly GPT-4.5. They highlight the incremental improvements in AI performance, the hallucination rate, and the growing trust in AI-generated content. The conversation also covers the increasing use of AI in healthcare, including for clinical decision support and medical education. They also debate the potential for AI to prescribe medications and the need for regulatory frameworks. 1. The Evolving Role of AI in Medicine: Progress and Persistent Limitations – While LLMs continue to improve, accuracy and reliability remain challenges, especially in high-stakes applications like healthcare. 2. Physician Adoption of AI: Benefits and Risks – With up to a third of doctors using AI for clinical decision support, concerns about over-reliance and unverified outputs must be addressed 3. AI’s Potential in Medical Education – From personalized learning to communication coaching, AI could revolutionize medical training and challenge outdated educational models. 4. AI in Prescribing Medications: Ethical and Regulatory Considerations – The idea of AI-driven prescribing raises ethical dilemmas and calls for a reassessment of healthcare delivery and professional licensure. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education. #healthcareai #healthcareprofessionals #aiinhealthcare

Get more information about Stanford's Online AI programs: https://stanford.io/ai The world is being reshaped by Artificial Intelligence. From revolutionizing industries to transforming how we work and live, AI is here to stay. Are you ready to be a leader in this exciting new era? Watch this online information session and discover a comprehensive suite of online AI courses taught by Stanford's leading faculty, the pioneers of AI research and innovation. In this session, you'll gain insights into what sets our courses apart: In-Demand Skills: Our courses are continually updated, enabling you to learn fundamental concepts, and the latest tools, and techniques driving the AI revolution. Flexible Learning: We offer courses to fit your schedule, learning style, and in a variety of topics within AI to enable you to achieve your unique learning goals. Proven Expertise: You will be learning directly from Stanford faculty, at the forefront of AI research and development. You will have access to course facilitators, office hours, or TAs to ask questions throughout the course. Don't miss this opportunity to unlock your potential and become a key player in the age of AI! Hear Q&A with our AI program managers, and receive useful guidance on applying and enrolling to join our thriving AI learning community. Browse Stanford's online AI programs: https://online.stanford.edu/artific... #artificialintelligence #ai #aicourse #learnai

Learn more about Stanford's online Healthcare AI programs: https://online.stanford.edu/artific... Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Hosts: Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Dr. Amy Abernethy, M.D., Ph.D., Co-founder, Highlander Health In this third episode of the Stanford AI in Healthcare podcast, hosts Justin Norden and Matthew Lungren, along with guest Dr. Amy Abernethy, Co-Founder of Highlander Health explore the transformative potential of AI in healthcare. Diving deep into the current capabilities of language models, the discussion tackles critical questions about AI adoption, clinical integration, and the evolving role of physicians. From ethical considerations to regulatory challenges, the conversation offers a nuanced look at how AI is reshaping medical practice, highlighting the delicate balance between technological advancement and human expertise. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education. #healthcareai #healthcareprofessionals #medicalinnovation

Learn more about Stanford's Healthcare AI programs: https://online.stanford.edu/artific... Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Kimberly Powell, Vice President / General Manager, NVIDIA In this episode, hosts Matt Lungren and Justin Norden welcome Kimberly Powell from Nvidia, who shares insights from her two-decade journey spearheading AI innovations in healthcare. They discuss recent AI advancements, the growing sophistication of patient interactions with AI models, and the shift toward employing robotics and digital tools in clinical settings. The conversation highlights how technology is evolving to enhance healthcare delivery and patient empowerment while addressing the challenges of privacy and compliance in medical environments. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education.

Learn more about Stanford's online Healthcare AI programs: https://stanford.io/3ETLFCx Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Peter Lee, President of Microsoft Research In this latest episode, hosts Justin Norden and Matthew Lungren, along with Microsoft Research President Peter Lee, discuss cutting-edge AI developments, focusing on model performance, post-training compute, and healthcare applications. The conversation explores emerging AI technologies, benchmarking challenges, and innovative approaches to medical diagnostics. Lee highlights research on sequential diagnosis, AI agents, and the potential of AI to reduce administrative burdens in healthcare. The discussion examines the nuanced evaluation of AI models, emphasizing the importance of creating collaborative, context-aware systems that can effectively assist medical professionals. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education. #healthcareai #MicrosoftResearch #generativeAI

In this insightful webinar, Dr. Nigam Shah, Professor of Medicine at Stanford University and Chief Data Scientist for Stanford Health Care, explores the transformative potential of artificial intelligence (AI) in healthcare systems. The application of AI in healthcare depends on how accurate the AI model is, the decision-making processes it informs, and how well healthcare professionals can act on the insights provided by AI. Learn more about the all new Applications of Machine Learning in Medicine program: https://stanford.io/49wbDXY #ai #artificialintelligence #machinelearning #healthcare

Get more information about Stanford's online AI programs: https://stanford.io/ai In this session, you’ll explore how AI products evolve from raw model outputs to real-world tools that drive value in production. We’ll break down how foundation models are refined after training, where emerging API capabilities are opening new doors for developers, and what separates successful GenAI apps from those that fall short. Hosted by Aditya Challapally (ML Engineer at Microsoft), with insights from Michelle Pokrass (Post-Training Research Manager at OpenAI) and Stanford Professor Chris Potts, this conversation reveals what it really takes to move from cutting-edge models to AI applications that are reliable, effective, and built to last. Browse Stanford's online AI programs: https://online.stanford.edu/artific...

October 22, 2024 Joshua Ott: https://profiles.stanford.edu/joshu... This lecture is from the Stanford graduate course AA228/CS238: Decision Making under Uncertainty This course introduces decision making under uncertainty from a computational perspective and provides an overview of the necessary tools for building autonomous and decision-support systems. Following an introduction to probabilistic models and decision theory, the course will cover computational methods for solving decision problems with stochastic dynamics, model uncertainty, and imperfect state information. Topics include Bayesian networks, influence diagrams, dynamic programming, reinforcement learning, and partially observable Markov decision processes. Applications cover air traffic control, aviation surveillance systems, autonomous vehicles, and robotic planetary exploration. Guest Lecture Slides: https://drive.google.com/file/d/19O... View the course website: https://aa228.stanford.edu/ Enroll in the course: https://online.stanford.edu/courses...

Explore the field of AI! This session provides a comprehensive overview of the Artificial Intelligence Professional Program, detailing each course and highlighting recommended learning paths for learners looking to study a particular focus area within the field of AI that resonates with their preferences, interests, or backgrounds. Explore the program: https://online.stanford.edu/program... Focus areas include: - Natural Language Processing - AI/ML Foundations - Robotics/RL - Generative AI - GNNs View our AI course selection resources: https://bit.ly/AI-Course-Selection Get more information about Stanford's online AI programs: https://stanford.io/ai Chapters: 0:00 Introduction 00:35 AI Professional Program Overview 03:05 Course Offerings 11:15 How to Create your Individualized Path 11:57 Course Groupings 12:34 Specialized Pathways based on topic 15:45 Course Rankings 19:05 Specialized Pathways based on background 20:09 Resources #artificialintelligence #learnai

Learn more about Stanford Online's AI in Healthcare programs: https://online.stanford.edu/artific... Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Hosts: Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Dr. Eric Topol, Scripps Research Translational Institute In this fourth episode of the Stanford AI in Medicine series, hosts Justin Norden and Matthew Lungren, and guest, Dr. Eric Topol of the Scripps Research Translational Institute, explore the transformative potential of #AI in healthcare, discussing how advanced technologies can revolutionize medical education, disease prevention, and patient empowerment. Drawing from his expertise in genomics and precision medicine, Dr. Topol reveals how AI can enable personalized health strategies, early disease detection, and individualized longevity approaches. The conversation critically examines current healthcare limitations while highlighting breakthrough opportunities in understanding age-related diseases, drug discovery, and patient-centered care. This discussion offers profound insights into how artificial intelligence is poised to reshape our understanding of health, aging, and medical innovation. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education. #healthcareai #healthcareprofessionals #medicalinnovation

Learn more about Stanford Online's AI in Healthcare programs: https://online.stanford.edu/artific... Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Hosts: Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Dr. Jessica Mega, Stanford University, MD, MPH In this 5th episode of the Stanford AI in Medicine podcast, hosts Justin Norden and Matthew Lungren and guest Dr. Jessica Mega explore AI's revolutionary potential in medicine, discussing its applications across diagnostic tools, drug discovery, and patient care. The conversation highlights the importance of developing AI platforms that integrate into clinical workflows, providing comprehensive patient insights. Drawing parallels with genomics research, the talk looks at AI's potential to break down medical specialization barriers and create more personalized, proactive healthcare solutions. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education. #healthcareai #digitalhealth #generativeAI

Learn more about Stanford's online Healthcare AI programs: https://online.stanford.edu/artific... Check out the AI in Healthcare series playlist: https://bit.ly/AI-in-Healthcare-YT-... Matt Lungren, Stanford University - https://profiles.stanford.edu/matth... Justin Norden, Stanford University - https://med.stanford.edu/profiles/j... Guest Speaker: Troy Tazbaz, Former Head of Digital Health for the FDA Join Matt Lungren and Justin Norden, faculty members at Stanford University, as they explore the dynamic and evolving landscape of artificial intelligence in healthcare. In this special episode, they are joined by Troy Tazbaz, the Former Head of Digital Health at the FDA, for a comprehensive and thought-provoking conversation on the intersection of AI, medicine, and regulation. This episode covers a wide range of critical topics: Adoption of Generative AI in Healthcare: Dive into the rapid adoption of generative AI technologies across various industries, with a specific focus on healthcare. The discussion covers the impact of tools like AI-driven chatbots and generative models on healthcare delivery, and how they are transforming the way medical professionals and patients interact. AI Performance Improvements and Human vs. AI: The episode highlights the remarkable advancements in AI performance, with AI models now outperforming humans in certain tasks and benchmarks. Matt, Justin, and Troy explore the implications of AI’s enhanced capabilities, particularly in areas like medical diagnostics, treatment plans, and patient outcomes, and discuss the ongoing debate about AI’s effectiveness compared to human clinicians. Regulatory Challenges and Frameworks: With Troy’s experience at the FDA, the episode delves into the regulatory landscape for healthcare AI. The conversation touches on the challenges of regulating rapidly evolving AI technologies, the frameworks needed to ensure safety, efficacy, and ethical use, and how regulators are balancing innovation with the need for oversight in a fast-moving field. Top-Down vs. Bottom-Up Adoption: The discussion also covers the contrasting approaches to AI adoption in healthcare, from bottom-up innovations driven by clinicians to top-down policies and regulations. The team explores the opportunities and obstacles in leveraging AI to improve healthcare delivery, providing insights from healthcare professionals, regulators, and academics alike. Tune in for expert insights into how AI is reshaping the future of healthcare, the challenges it brings, and how leadership, innovation, and regulation are key to navigating this transformative period in medicine. Stanford Online, in collaboration with the Stanford Center for Health Education, is brought to you by the Stanford Engineering Center for Global & Online Education. #healthcareai #healthcareprofessionals

Unlocking the true potential of generative AI starts with understanding how it works. This video—the first in a new educational series—introduces healthcare professionals to large language models (LLMs) like ChatGPT: what they are, how they generate responses, and how to use them thoughtfully. Join us as we explore: • How LLMs fit into the broader landscape of AI in healthcare • What actually happens behind the scenes when you submit a prompt • The core techniques that shaped today’s most powerful models — and what the future holds Drawing from both foundational literature and the latest developments, this series translates complex AI concepts into practical insights—no computer science background required. Shivam Vedak, MD, MBA - https://medicine.stanford.edu/profi... Dong-han Yao, MD - https://med.stanford.edu/profiles/d... More about the speakers: Shivam Vedak, MD, MBA, and Dong Yao, MD, are physicians and clinical informaticists at Stanford Medicine. Their work focuses on the practical application of generative AI in healthcare, bridging system-level implementation and frontline clinician education. They have been invited to present and teach on this topic at academic institutions and conferences nationwide, reaching a diverse audience of physicians, healthcare IT professionals, and other clinical leaders. Chapters: 0:00 — Introductions and Disclosures 2:50 — Why Is Prompting Hard? 6:55 — The Three Epochs of Healthcare AI 18:01 — Tokenization and Embeddings 27:58 — Transformer Architecture and Self-Attention 34:45 — Pre-Training and the Evolution of LLMs 44:01 — Post-Training: Making the Model Helpful and Aligned 49:29 — The Reasoning Era: Scaling Test-Time Compute 54:18 — Summary: What Is an LLM?

Get more information about Stanford's online AI programs: https://stanford.io/ai Beiliei Zhu, Kuniaki Iwanami, and Ricardo LaRosa share their thoughts on the AI Professional Program. Artificial intelligence is transforming the world and helping organizations of all sizes grow, innovate, and make smarter decisions. The Artificial Intelligence Professional Program will equip you with knowledge of the principles, tools, techniques, and technologies driving this transformation. You can learn more about the program here: https://online.stanford.edu/program...

For more information about Stanford's Artificial Intelligence programs visit: https://stanford.io/ai In recent years AI has taken center stage with the rise of Large Language Models (LLMs) that can be used to perform a wide range of tasks, from question answering to coding. There is now a strong focus on large pretrained foundation models as the core of AI application development. But on their own, these models don’t do much besides taking up significant disk space—it’s only when they’re embedded within larger systems that they start to deliver state-of-the-art results. In this webinar, Professor Christopher Potts will discuss how AI systems built with multiple interacting components can achieve superior results compared to standalone models. He will also examine how this systems approach impacts AI research, product development, safety, and regulation. View AI Professional Program: https://online.stanford.edu/program... View AI Graduate Program: https://online.stanford.edu/program... Chapters: 00:00 - Introduction 00:14 - The Present and Future of Compound Systems 00:38 - Large Language Models and Industry Trends 00:55 - The Impact of GPT-3 on AI 01:07 - Google PaLM and Model Announcements 01:41 - OpenAI's Transition to Systems Thinking 02:01 - Building Effective AI Systems 02:23 - Minimal System for Model Interaction 02:56 - Importance of Prompting and Sampling Methods 03:22 - Various Sampling Techniques 04:04 - Chain-of-Thought Reasoning 04:30 - Majority Completion Strategies 05:00 - Exploring Innovative Sampling Techniques 05:37 - Importance of Systems Thinking 05:56 - Tool Access and System Design 06:40 - Understanding the Evolution of Google Search 06:58 - Scaling Systems for AI 07:53 - Learning from Past Experiences 08:04 - Guardrails and Regulation 09:53 - The Future Impact of AI on Society 10:34 - Insights for Technical and Business Leaders 11:18 - DSPy Learning Resources 12:00 - Final Thoughts on Systems Thinking 12:38 - Conclusion and Q&A Session

For more information about Stanford's Artificial Intelligence programs visit: https://stanford.io/ai In this webinar, you will gain an introduction to the concept of agentic language models (LMs) and their usage. You will learn about common limitations of LMs and agentic LM usage patterns, such as reflection, planning, tool usage, and iterative LM usage. This online session will cover: Overview of LMs LM Usage and limitations Retrieval Augmented Generation (RAG) Tool usage Agentic LMs Agentic design patterns About the speaker: Insop Song Insop is a Principal Machine Learning Researcher at GitHub Next. Previously he worked at Microsoft, where he focused on leveraging machine learning and large language models to boost engineering productivity. His projects included fine-tuning open-source large language models with internal code and text, developing document assistance tools, and applying AI to various engineering tasks. He is currently a course developer as well as a course facilitator for Stanford Online’s professional AI program. Chapters: 00:00 - Introduction 00:10 - Overview of the Talk 01:50 - Training Language Models 02:30 - Modeling Objectives 04:00 - Examples of Training Data Formatting 05:40 - Applications of Language Models 06:50 - Using API for Language Models 09:00 - Best Practices for Prompt Preparation 11:10 - Importance of Clear Instructions 13:40 - Reflection and Improvement Techniques 16:30 - Tool Usage and Function Calling 20:30 - Definition of Agentic Language Models 21:50 - Reasoning and Action in Agentic Models 24:00 - Example of a Customer Support AI Agent 29:20 - Summary of Applications 36:00 - Key Design Patterns in Agentic Models 44:00 - Summary of Agentic Language Model Usage 47:40 - Audience Q&A 50:00 - Addressing Ethical Considerations 54:50 - Getting Started with Language Models 57:00 - Resources for Staying Updated 58:20 - Closing Remarks