I gave this talk at TSAAPT (Texas Section of the American Association of Physics Teachers) spring meeting. 0:00 Bloom's 2-sigma problem 1:50 Our first version and core teaching philosophy 2:54 Failing can be fun? 3:46 Prerequisites Graph 5:25 Gamification 6:00 Spaced Repetition and Fractional Implicit Review 7:19 The Good News 8:09 Making it AP Physics 8:58 The Bad News 9:38 The Rewrite 9:52 1. Teach one concept at a time 10:18 2. Build missing prerequisites 11:06 3. 3blue1brown-style animations 11:51 Multiple Choice is Bad 13:13 4. New question types 15:49 Where 1:1 tutoring and classrooms still win 17:04 PhysicsGraph in the classroom If you're interested in a pilot, contact information is on the last slide! https://physicsgraph.com https://x.com/physicsgraph https://x.com/jeffreybiles

Train in hardcore physics skills at https://physicsgraph.com/ Social media: https://x.com/jeffreybiles

https://physicsgraph.com/ 0:00 Intro 0:38 Learning topics before you're ready 3:19 "Learning" stuff you already know 6:48 Skipping practice problems 10:03 Forgetting 12:40 (classic) wasting time "You're not dumb, you're just missing the prerequisities": https://lelouch.dev/blog/you-are-probably-not-dumb/ https://x.com/jeffreybiles

https://physicsgraph.com Check out our quantum computing course - you only need high school math (algebra and trigonometry), and we'll teach you the rest. And if you're reading this in the future, check out our other courses as well! https://x.com/jeffreybiles

Vibe-coding is a lot better than I thought it would be, and really useful, but there are still challenges - especially for non-developers Get double the starting credits with this link: https://lovable.dev/jeffreycodes 0:00 Intro 0:14 The first try - a beautiful mess 2:45 Our Project Plan - start simple! 5:07 How to follow along - Lovable.dev 6:01 Displaying data with a simpler prompt 7:45 Looking at generated code 8:40 Connecting to Supabase backend 14:09 When do you need to understand the code? 15:30 Auth 17:53 A huge signup gotcha 21:20 Reviewing our project plan 21:58 When should you NOT use vibe-coding? 24:09 Creating new products - forms, uploading images, creating records in the database 27:53 Using tokens to purchase a product 29:45 Fighting the AI - Error Loops 33:27 Limits of Vibecoding for nontechnical people 34:19 ProductPurchase table + fun error 36:48 Buying with Stripe 39:37 Checkout page issues 41:21 Vibe-coding is amazing, but… https://x.com/jeffreybiles

AI Engineering for Software Developers, part 2 Get the full roadmap here: https://www.jeffreycodes.com/ai-engineering Buy the book here: https://www.oreilly.com/library/view/ai-engineering/9781098166298/ 0:00 Intro 0:46 What you don't need to know 2:05 Transformers vs Mamba vs Diffusion 3:07 Pre-training 4:37 Common Crawl and "internet data" 5:40 Domain-specific data (AlphaFold, etc.) 6:48 Post-training 7:18 Behavior Cloning (Supervised FineTuning) 9:16 Structured Outputs and how to fix them 10:40 RLHF (Reinforcement Learning from Human Feedbakc, Preference FineTuning) 11:45 Pros and cons of RLHF 12:52 Why hallucinations happen 14:18 Temperature 15:13 Test Time Compute and Reasoning 16:30 Compute Optimal 17:15 Models: size vs speed vs quality https://x.com/jeffreybiles

Download full roadmap for free: https://www.jeffreycodes.com/ai-engineering Buy the book: https://www.oreilly.com/library/view/ai-engineering/9781098166298/ 0:00 Why read this book and watch this series? 1:09 Download the roadmap 1:22 AI Engineering vs ML Engineering (vs Software Engineering vs AI Research) 4:52 Where you shouldn't put AI (and where it's okay) 7:22 AI use cases 10:58 Preview of chapters 2-10 Playlist here: https://www.youtube.com/playlist?list=PLPwpWyfm6JADMaDy7Fs9wJMuBocBagwAz (video 2 coming out next week) https://x.com/jeffreybiles

This morning I read the final chapter in AI Engineering (it's a great book!) and finished up the the concept map. Next up: making a full-length video on it, and then moving on to other projects! https://x.com/jeffreybiles

My first attempt at a YouTube Shorts, let me know what you think of the format https://x.com/jeffreybiles

0:00 Overview 0:32 LLM Routing vs web app routing 1:43 Phone Tree example 3:02 Help Chat example 4:02 Classifying with keywords 5:43 Classifying with LLMs 8:19 Importance of an Eval Suite for Prompt Engineering 9:22 Routing goals 10:02 Re-introducing Infinite Cookbook 11:28 Implementing Routing 13:46 Error handling for irrelevant URLs 14:32 Fewer UI elements means fewer affordances 15:23 Actually using an LLM for Routing 16:59 When it's better to have a separate UI element 19:50 Example app review 20:29 Routing Workflows vs Agency https://x.com/jeffreybiles

0:00 Overview 0:44 Natural Interest 3:14 Usefulness 6:08 Learning Plan 8:25 Productivity Tricks If you're a computer science student or working software developer and want an excellent learning path to grow useful skills, check out CodeCrafters: https://app.codecrafters.io/join?via=jeffreybiles The math course I reference is MathAcademy (not sponsored, but they should...) https://mathacademy.com/ Bonus tip: sign up for my new company https://physicsgraph.com/. It's like MathAcademy for Physics https://x.com/jeffreybiles

In 2024 I studied a ton of math, computer science, ML/AI, and data engineering - all while holding down a full-time job and welcoming our first child. Here's all the secrets to how I did it. Video about what I learned in 2024: https://youtu.be/dk3dQf7yZFI Tips I forgot for the video: * take breaks throughout the day. Not on your phone - you need to look away from a screen for at least 5 minutes. If you're working from home, this is a great time to play with your children or do small chores! * take 1 day off per week. Take care of things around the house, be with your family, maybe go see friends and extended family with them as well * accept changes as they come. Just today I stayed up late editing the video, slept in for 3 hours, then took care of the baby for an hour and a half because a sitter didn't show up. But I'll be back to normal tomorrow. Update: I changed title from "study" to "studied" for a couple reasons: * My non-day-job work is now a mix of studying, projects, and YouTube * I'm switching schedules to one where the big block is closer to 3 hours, so that family dinner time is easier. I'll probably switch again at some point as circumstances change! CHECK OUT MY NEW COMPANY: https://physicsgraph.com/ 0:00 Intro 0:24 Organizing my time 1:51 Cut hobbies 3:04 Work from Home 3:34 Pay for free time 4:08 Marry well 5:06 Multi-task intelligently 6:42 Work up your stamina 7:22 Switch up your environment 9:12 Get good sleep 9:35 Work out 10:22 Focus 11:04 Have a "default activity" 12:33 Think long-term 13:32 Take time off 14:42 Have fun Want to study intermediate computer science and software engineering with guided projects? Check out codecrafters (affiliate link, but they're high-quality): https://app.codecrafters.io/join?via=jeffreybiles https://x.com/jeffreybiles

I'm building my first real app that uses LLM output to power the entire thing. Not just another chatbot, but something that combines a more traditional UI and more traditional set of software engineering practices with the new possibilities of LLMs. 0:00 Intro 0:29 Why this type of app? 1:36 Generating JSON in the Groq Playground 3:21 Tradeoffs of a smaller/faster model 4:30 App architecture for generating recipe ideas 7:18 Recipe Generation 8:25 Validation using LLMs and JSON 9:50 Extracting data from the recipe 10:37 Handling failure when generating JSON 12:48 Other cool features https://x.com/jeffreybiles

Links to favorite resources below Exercises PhysicsGraph (MY NEW COMPANY!): https://physicsgraph.com/ MathAcademy: https://mathacademy.com/ NeetCode Roadmap: https://neetcode.io/roadmap CodeCrafters (affiliate link, but the course I tested was quite good): https://app.codecrafters.io/join?via=jeffreybiles Books Designing Data Intensive Applications: https://www.amazon.com/Designing-Data-Intensive-Applications-Reliable-Maintainable/dp/1449373321 Hands On Machine Learning: https://www.amazon.com/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/1098125975 YouTube 3blue1brown: https://www.youtube.com/@3blue1brown StatQuest: https://www.youtube.com/@statquest CoreDumped: https://www.youtube.com/@CoreDumpped Andrej Karpathy: https://www.youtube.com/@AndrejKarpathy Video Courses MIT 18.06SC Linear Algebra: https://www.youtube.com/playlist?list=PL221E2BBF13BECF6C MIT 6.042J Mathematics for Computer Science: https://www.youtube.com/playlist?list=PLUl4u3cNGP60UlabZBeeqOuoLuj_KNphQ MIT 6.004 Computation Structures: https://www.youtube.com/playlist?list=PLDSlqjcPpoL64CJdF0Qee5oWqGS6we_Yu Build a 65c02 Computer from Scratch: https://www.youtube.com/playlist?list=PLowKtXNTBypFbtuVMUVXNR0z1mu7dp7eH Great response video about how to learn AI: https://www.youtube.com/watch?v=5FM_0RUJhYo 0:00 Intro 0:25 Why I started studying 1:20 Math 3:45 Computer Science 5:25 Leetcode and Algorithms 6:41 Data Engineering 7:44 ML/AI 9:01 Reflections 10:30 Scattered Attention 11:21 What I'd do differently https://x.com/jeffreybiles

Cursor has replaced VSCode and ChatGPT in my coding workflow. Let's take a look at what features it has, how I've been using it, and where it still falls short. https://www.cursor.so/ Find me online: https://www.jeffreybiles.com https://twitter.com/jeffreybiles