
Peter Yang
@petergyang • 244,122 subscribers
Practical AI tutorials and interviews for busy people | Get my best AI skills and guides at https://t.co/6VAA6p81x6
Shorts
Videos

Anthropic recently cut Claude Code’s system prompt by 80%. Thariq explains why: “As the models have gotten smarter, they need less direction, fewer constraints, and fewer examples. The examples are constraining it because now it’s like, ‘Oh, you want things like this example.’ If you remove the examples, it can actually be more free-form. All this is to say that you want to trim your context [when a new model is released]. The latest models often need more room to run.” 📌 Watch the full episode here:
Peter Yang222,445 views • 13 hours ago

You can now make videos like this using HTML. I didn’t believe it at first until the HyperFrames team showed me how they do it directly in Codex and Claude Code. Best of all, the tool is 100% free and open source. But you need to learn the right workflows to make the videos look great - including generating a frame.md, storyboards, and more. 📌 Subscribe to get our full tutorial tomorrow:
Peter Yang187,501 views • 29 days ago

The only concert venue where the nosebleed seats are better than the front row.
Peter Yang4,648,247 views • 2 years ago

"This will replace 80% of the apps that you have on your phone." Here's my new episode with Peter Steinberger 🦞 where he showed me: ✅ His personal OpenClaw use cases - flight check-in, home security, and much more ✅ His counterintuitive AI coding workflow - no plan mode, no MCPs, and no fancy prompts ✅ Practical advice for other builders and how to build product taste Some quotes from Peter: "It's like having a new weird friend that is also really smart and resourceful that lives on your computer." "Why should I use MyFitnessPal when I have an infinitely resourceful assistant that already knows I'm making bad decisions at KFC?" "I don't use MCPs or any of that crap. Just because you can build everything doesn't mean you should." 📌 Watch now: Thanks to our sponsors: Granola - The best AI meeting notes app I've ever used: Replit ⠕ - Create beautiful prototypes and full stack apps:
Peter Yang666,628 views • 5 months ago

"We (Anthropic) are now creating entire features in days, not weeks." Here's my new episode with jenny wen (Claude's Head of Design) where she gave me a rare look at how Anthropic operates, including: ✅ How she uses Cowork to build products ✅ The real story behind Cowork's creation (including screens of early Cowork prototypes) ✅ How Anthropic is able to ship every day Some quotes from Jenny: "The specs we used to make with milestones ...we don't really do that anymore." "People think we built Cowork in 10 days. The actual story is we've been prototyping this direction for a year." "Designers, if you feel like the ground is shifting beneath your feet, it's because it is." 📌 Watch now: Thanks to our sponsors: Replit ⠕: Plan, design, and build with AI agents Linear: The AI agent platform for modern teams
Peter Yang426,439 views • 3 months ago

Asked GPT 5.5 and Codex to make Star Fox. This is after 15 min of prompting 🔥
Peter Yang259,531 views • 2 months ago

"We write very few specs on the Codex team. We're talking 10 bullet points and that's it." Here's my new episode with Alexander Embiricos and Romain Huet where they gave me an inside look at how OpenAI's Codex team operates: → Live demo: Building in seconds with Spark → How the team built the beautiful Codex app → How they ship without traditional specs and roadmaps Some quotes from Alex and Romain: "The fewer people you need in a room to do anything, the more pure every decision is." "Our designers write more code now than was written by an engineer six months ago." "I'm much less likely to read someone's resume than their ideas and what they've built." Thanks to our sponsors: Granola: The best AI meeting notes app I've ever used Linear: The AI agent platform for modern teams 📌 Watch now:
Peter Yang290,423 views • 3 months ago

"I'm not an engineer but somehow I'm able to ship things of value, which is crazy and weird and still blowing my mind." Here's my new episode with Matt Van Horn, a non-technical founder who has contributed to 100+ open source projects and reached 44K+ GitHub stars despite not knowing how to code. We cover: → How he uses Compound Engineering to build without reading code or plans → How you can use Printing Press to give your agent access to almost any website or app → How he contributed to Python, Go, OpenClaw, and other top repos Some quotes from Matt: "My favorite tool for building anything is Compound Engineering. The killer skills are CE plan and CE work." "What if anyone could print their own CLI? Google Flights and Kayak don't have an official API, but Printing Press lets you find all the secret APIs that exist." "Just build, just launch. It's okay even if you build something for yourself. Even if I had no users of Agent Cookie, I get value out of it." 📌 Watch now: Thanks to our sponsor: Riverside: All-in-one AI studio for podcasts and video Wispr Flow: 4x faster than typing with your voice
Peter Yang94,838 views • 1 month ago

"I shipped 9 failed products before one took off...now I'm doing $1M+/month." Here's my new episode with Tibo, a solo founder who bootstrapped 5 AI products to $1M+ / month. Tibo walked me through his exact playbook: ✅ How to validate ideas and fail fast ✅ Why his top acquisition channel is still SEO ✅ The pricing sweet spot for AI products Some quotes from Tibo: "When people twist your product into something else, that's a very strong signal you have to follow." "It's easy to lie to yourself [with free users], but if there's no stickiness in the revenue, it's very hard to build a successful business." "I'm convinced right now that just one person can do the job of 20 people." 📌 Watch now: Thanks to our sponsors: Wispr Flow: Don't type, just speak Linear: The AI agent platform for modern teams
Peter Yang207,804 views • 2 months ago

"I've spent $30K on a launch video, now you can make one with code." Here's my new episode with Bin Liu and Jake Moran, where they shared their 5-step playbook for using HyperFrames to make professional launch videos in Codex and Claude Code: 1. Gather video assets and create a frame.md 2. Create a storyboard.md with the scenes 3. Pull animations from the HyperFrames repo 4. Generate and review static frames 5. Build the video with HyperFrames Studio You can also start simple by using the built-in /website-to-video skill to one shot a launch video from any URL. HyperFrames is 100% free and I love how it democratizes video creation for everyone. 📌 Watch now: Thanks to our sponsors: Wispr Flow: 4x faster than typing with your voice Riverside: All-in-one AI studio for podcasts and video
Peter Yang68,646 views • 28 days ago

I thought Dune 2 was the best movie of 2024 until I watched this masterpiece (sound on).
Peter Yang1,536,723 views • 2 years ago

"My job is to automate my job. That's all of our jobs from now on." Here's my new episode with Geoff Charles (CPO Ramp) where he shared the best AI-native company playbook I've seen so far, including: ✅ His go-to Claude Code skill to turn ideas into great products ✅ Exclusive demos of AI agents that Ramp built for customer research, data, and coding. ✅ The L0-L3 framework to get every employee to ship production code Some hot takes from Geoff: "If you're not in Claude Code, no matter what your role is, you're probably underperforming." "I still see very high performing PMs who don't get it. That is the biggest danger." "Management is probably dead. What you should be optimizing for is to become the best builder in the world." 📌 Watch now: Thanks to our sponsors: Granola - The best AI meeting notes app I've ever used: Replit ⠕: Try Agent 4 to turn ideas to apps in minutes:
Peter Yang242,862 views • 4 months ago

"I woke up and he already built a website, created a product, set up Stripe, and launched." Here's my new episode with Nat Eliason on how he set up his OpenClaw bot, Felix Craft, to build a business that made $14,718 in 3 weeks. We talked about: ✅ The 3-layer memory system that prevents your bot from forgetting things ✅ How to run 5 chats with your bot at the same time ✅ How to safely give your bot Stripe, Vercel, and X access Some quotes from Nat: "Every time Felix asks me to do something, I ask: Can I remove this bottleneck so you never have to ask me this again?" "I'm never in Claude Code or Codex myself anymore. I just tell Felix to do it." "If you get the memory system and the proactivity right, it solves 90% of the frustrations that most people run into." 📌 Watch now: Thanks to our sponsors: Linear: The AI agent platform for modern teams Replit ⠕: From 0 to full stack app in 2 min.
Peter Yang230,230 views • 4 months ago

"If you're in tech, run in one of these directions." In this clip, Amjad Masad (CEO Replit ⠕) shares two paths to future-proof your career in the AI era: 1. Get as close to the metal as possible (e.g., NASA won't use GPT-Javascript to run rockets) OR 2. Become a generalist who can go from idea to end product with AI end to end. Amjad and I had a great chat covering: • Why now's the best time to learn to code • A live demo of building a nutrition tracker app • The rise of personal apps and the future of work Some quotes from Amjad: "The return on learning to code doubles every 6 months. AI automates many of the boring parts. What's left is you and your creativity — the most exciting part of coding." "The ultimate test for an AI coding agent is if you can make an app faster than you can Google for it. I think we've done it." "I’ll be honest with you. I think roadmaps are dead. Here's why..." 📌 Watch now:
Peter Yang740,699 views • 1 year ago

This is the most complete setup I've seen yet to turn Claude Code into your personal OS. Here's my new episode with Moritz Kremb where he shared the system that runs his email, content, and even grocery shopping. We talked about: → The 4 layers: folders, tools, skills, routines → Memory: Set up a nightly "dreaming" job → Tools: The best CLIs and MCPs to use → Skills: Video edits, planning, and more → Routines: When to use local vs. remote 📌 Watch now: Thanks to our sponsors: Wispr Flow: Don't type, just speak Linear: The AI agent platform for modern teams
Peter Yang113,564 views • 2 months ago

Here's my new episode with Alex Albert, who shared an inside look at how Anthropic is building the next Claude. We talked about how the research team: → Plans for the model and harness together → Uses Claude to turn user feedback into evals → Trains Claude's character & personality Some quotes from Alex: "We use Claude to cluster user feedback, find top themes, and create synthetic versions of user problems that we then turn into evals." "We need to think about how the model is exposed through all our surfaces, whether it's API or Claude Code or Cowork. The product has a blend with the model and that affects your end user's experience." ""As these things become agents running tasks for a long time and making judgment decisions, what its character is and what it cares about are very important." 📌 Watch now: Thanks to our sponsors: Wispr Flow: Don't type, just speak Oceans: Hire AI-native executive assistants
Peter Yang94,599 views • 2 months ago