AI Tinkerers - "One-Shot"

Sam Hesson, a technical founder turned Meta AI incubations engineer who built agentic CI/CD pipelines, tells wild stories and explains his architecture. He covers his $50k token-abundance mindset. Short, punchy dives into converting Ray-Bans conversations to PRDs, running parallel competitive agents, rubric-based LLM judges for self-healing PRs, and prepping codebases for reliable agent testing.

Eric Simons, founder and CEO of StackBlitz, built browser-first dev tooling and led the pivot to Bolt. He walks through the rapid pivot from WebAssembly-based browser runtimes to vibe coding. Topics include the Sonnet 3.5 model breakthrough, running full Node.js in-browser, Bolt’s explosive ARR growth, web container economics, live one-prompt app demos, shifting product roles, and security considerations.

Andrew Baker, a former Twilio engineer and creator of innovative projects like an airline seat selector, shares his fascinating journey into browser automation. He discusses the evolution of sophisticated agents that tackle real-world tasks and the technical hurdles they encounter, such as DOM complexity and authentication issues. Baker also showcases 'Claude Draws', his AI-enhanced revival of the classic Kid Pix app, revealing how nostalgia meets creativity through automation. Tune in for insights on shaping the future of browser-native agents!

Lukas Biewald, founder of CrowdFlower and Weights & Biases, shares his journey from tinkering with robot cars to leading AI companies. He discusses the importance of hands-on ML experiences that shaped him and how his early projects inspired tools like Weights & Biases. Lukas also delves into 'vibe coding' with his daughter, effectively merging play and learning, while highlighting the importance of observability in AI production environments. He explores the future of AI, touching on reinforcement learning as a promising avenue for improvement.

Steve Yegge, an experienced software engineer known for his work at Amazon and Google, discusses his innovative Beads framework, which enhances AI coding agents with session memory and task management. He explains how Beads revolutionizes developer workflows, allowing AI to manage complex projects like a pro. The conversation goes into the future of engineering roles, emphasizing a shift from coding to supervising AI. With insights on multimodal tools, automated validation, and enabling junior developers, Steve reveals how to harness the power of AI in coding.

What if your home robot didn’t just clean, but felt alive — learning, adapting, and becoming part of your family?In this episode of AI Tinkerers One-Shot, Joe talks with Axel Peytavin, Co-founder & CEO of Innate, about his mission to create robots that aren’t just functional, but truly responsive companions. From his early start coding at age 11 to building one of the first GPT-4 Vision-powered robots, Axel shares how his team is creating an open-source robotics kit and one of the first agentic frameworks for robots — giving developers the tools to teach, customize, and build the next generation of embodied AI.What you’ll learn:- Why Axel believes “robots that feel alive” are the future — beyond flashy demos of backflips and kung fu.- How Innate is making robotics accessible with an open-source hardware and SDK platform.- The breakthroughs (and roadblocks) in fine motor manipulation, autonomy, and real-time learning.- How teleoperation, deep learning, and reinforcement learning are shaping the next era of household robots.- Axel’s vision for robots as companions: cleaning, tidying, assisting — and even calling for help in emergencies.Whether you’re a tinkerer, developer, or just curious about how soon robots will fold your laundry, this deep dive shows what’s possible now — and what’s coming next.💡 Resources:- Innate Robotics – https://innate.bot/- Axel Peytavin’s Twitter – https://x.com/ax_pey/- AI Tinkerers – https://aitinkerers.orgSubscribe for more conversations with the builders shaping the future of AI and robotics!0:00 Axel’s mission — building robots that feel alive00:57 The open-source kit that lets any tinkerer train new behaviors05:00 Why applied mathematics is the foundation for AI + robotics08:17 Early projects: Minecraft plugins with 200K+ downloads11:04 Innate’s vision for teachable household robots12:01 Why fine-motor manipulation is the real breakthrough, not backflips15:19 How deep learning is driving rapid robotics progress17:11 Teleoperation as the engine for data collection and training23:21 Why tidying up, laundry, and dishes are the killer apps for home robots32:24 Live teleoperation demo of Maurice in action36:08 Breaking down the system architecture — Wi-Fi, WebSockets, Python SDK41:40 Maurice shows delicate fine-motor skills with object pickup43:53 How Innate built one of the first agentic frameworks for robots49:50 The rise of an open-source robotics community around Maurice57:03 Viral GPT-4 Vision robot demo — and what it revealed about the future

Learn how to demystify large language models by building GPT-2 from scratch — in a spreadsheet. In this episode, MIT engineer Ishan Anand breaks down the inner workings of transformers in a way that’s visual, interactive, and beginner-friendly, yet deeply technical for experienced builders.What you’ll learn:• How GPT-2 became the architectural foundation for modern LLMs like ChatGPT, Claude, Gemini, and LLaMA.• The three major innovations since GPT-2 — mixture of experts, RoPE (rotary position embeddings), and advances in training — and how they changed AI performance.• A clear explanation of tokenization, attention, and transformer blocks that you can see and manipulate in real time.• How to implement GPT-2’s core in ~600 lines of code and why that understanding makes you a better AI builder.• The role of temperature, top-k, and top-p in controlling model behavior — and how RLHF reshaped the LLM landscape.• Why hands-on experimentation beats theory when learning cutting-edge AI systems.Ishan Anand is an engineer, MIT alum, and prolific AI tinkerer who built a fully functional GPT-2 inside a spreadsheet — making it one of the most accessible ways to learn how LLMs work. His work bridges deep technical insight with practical learning tools for the AI community.Key topics covered:• Step-by-step breakdown of GPT-2 architecture.• Transformer math and attention mechanics explained visually.• How modern LLMs evolved from GPT-2’s original design.• Practical insights for training and fine-tuning models.• Why understanding the “old” models makes you better at using the new ones.This episode of AI Tinkerers One-Shot goes deep under the hood with Ishan to show how LLMs really work — and how you can start building your own.💡 Resources:• Ishan Anand LinkedIn – https://www.linkedin.com/in/ishananand/• AI Tinkerers – https://aitinkerers.org• One-Shot Podcast – https://one-shot.aitinkerers.org/👍 Like this video if you found it valuable, and subscribe to AI Tinkerers One-Shot for more conversations with innovators building the future of AI!

In this episode of AI Tinkerers Global Stage, we go deep with Steve Krenzel, founder of LogicLoop and ex-CTO office at Brex. Steve shows us how his company turns standard operating procedures (SOPs) into fully functioning APIs—complete with schema generation, test cases, structured outputs, and backtesting—within seconds.We break down:1. Why Steve avoids agentic frameworks2. How Logic automates 100K+ tasks/month for real customers3. The power of structured output for reasoning and reliability4. How prompt caching and append-only templates unlock scale5. His open-source coding agent that builds software from scratch6. How they achieved less than 2% error rates beating human teams7. His famous Prompt Engineering Guide that went viral in 2023If you’re building with LLMs, designing autonomous workflows, or just want to see what the future of developer productivity looks like—this is a must-watch.

Discover how Robert Lukoszko, CEO of Stormy AI, is building the future of AI-powered marketing by automating influencer outreach end-to-end. This interview goes deep into his journey from viral AI demos to Y Combinator, revealing critical insights for AI builders and founders.You’ll learn: • The surprising challenges and limitations of building AI applications that deeply integrate with operating systems. • Why local AI models, despite their appeal, often struggle to compete with cloud-based solutions for real-world business cases. • Robert’s unique approach to AI-assisted development, leveraging tools like Claude 3.7 for rapid prototyping and efficient coding. • How Stormy AI uses advanced AI to find niche influencers, analyze engagement, and automate outreach, transforming traditional marketing. • The strategic importance of distribution and market fit over pure technological innovation for venture-scale AI companies.Robert Lukoszko, previously co-founder of Fixkey AI (acquired) and an alumnus of Y Combinator (S24 with Stormy AI, W22 with ngrow.ai), shares his extensive experience in applying AI to new modalities and building high-growth startups.This episode of AI Tinkerers One-Shot offers a practical look at the technical and entrepreneurial realities of building in the generative AI space.💡 Resources: • Stormy AI - https://stormy.ai • Robert Lukoszko’s LinkedIn - linkedin.com/in/robert-lukoszko • AI Tinkerers - https://aitinkerers.org • One-Shot Podcast - https://one-shot.aitinkerers.org/Social Media: @AITinkerers @stormy_hq@Karmedge👍 Like this video if you found it valuable, and subscribe to AI Tinkerers One-Shot for more conversations with innovators building the future of AI!00:00 – Introduction & Background02:38 – Visual AI, Demos & Startup Idea06:27 – Local vs. Cloud Models10:07 – Desktop AI App & Context Importance14:11 – Building the App & OS Integration23:13 – Ambient AI & Contextual Vision32:17 – Stormy AI Pivot & Demo38:35 – AI Mindset & Content Creation43:57 – AI Model Comparison & Cost

Kyle Corbett, founder of OpenPipe, shares insights on enhancing AI agents through fine-tuning and reinforcement learning. He reveals how RL can cut error rates by 60% and reduce latency, making AI agents more reliable. Listeners learn about building an effective email search agent that surpasses GPT-3.5, using the Enron dataset for realistic training. Kyle also discusses the importance of designing nuanced reward functions and highlights ideal use cases for RL fine-tuning, including real-time voice assistants and high-volume applications.