List from buildsoftwarewithai.com
AI for Developers
Tools, techniques and ideas for building software with AI.
Latest videos
Newest first
The New Code Owner Didn't Write the Code
In a software factory, the code owner didn't write the code. Maria Gorinova explains Tessl's steward role: someone responsible for a repo who makes sure the dark factory works well there, without typing the code themselves. Watch the full episode at https://youtu.be/wrRxw15s31k or listen wherever you get your podcasts
Per-Seat Vendors Are Getting Crushed
Per-seat vendors are getting crushed, says Jason Lemkin. "If you fight it you're gonna end up in a spiral." The AI and agent-friendly apps are on fire. Adapt or fade.
Teaching Kids Programming with Pi
A small little demo of a dungeon crawler I build with my kids, and how I'm using an agent to also explain how it works so they can better understand it. Code: https://github.com/mitsuhiko/dungeon-crawler Game: https://mitsuhiko.github.io/dungeon-crawler/ Interactive Learn Page: https://mitsuhiko.github.io/dungeon-crawler/learn/ The agent uses pi-durable: https://github.com/earendil-works/pi/tree/main/packages/durable
Meta's Muse is the best AI agent I've tested
Claire benchmarked Meta's Muse against 8 models. It ranked 1st on agentic work: billing tickets, inbox triage, overnight research, and voice assistant tasks. Full episode of How I AI with Claire Vo is out now.
Weeks to Hours: SentinelOne on Cybersecurity Research with OpenAI
Cybersecurity research, moving from weeks to hours. SentinelOne’s Gregor Stewart describes OpenAI’s cyber capabilities reaching human-level output in about eight hours on reverse-engineering work that would take a top researcher four to six weeks. That lets security teams investigate more malware, connect related threats and keep a clearer picture of how attacks are evolving. “That’s a kind of intelligence that we were never able to afford before.” Watch Gregor explain what faster research makes possible.
Fully Connected 2026 Day 2: Mike Intrator on Hot Ones, Parag Agrawal, Dylan Patel, and Jenson Button
CoreWeave Fully Connected 2026 Day 2: CoreWeave CEO Mike Intrator takes the Hot Ones hot seat with Sean Evans, plus keynotes from Parag Agrawal, Dylan Patel, and Formula One World Champion and Aston Martin Aramco F1™ Team ambassador Jenson Button. Day 2 was about what happens after the launch: scaling infrastructure, cutting operational friction, and keeping teams sharp when the stakes are high. Parag Agrawal, founder and CEO of Parallel Web Systems, explains how agents are reshaping the web. Dylan Patel, founder of SemiAnalysis, breaks down cloud security across the full stack. Formula One World Champion Jenson Button talks about building team culture under pressure. Then Mike Intrator works through the wings while Sean Evans asks the questions. *What CoreWeave Forge is and what's in it:* https://www.coreweave.com/forge *Forge docs, quickstarts, and API references:* https://docs.coreweave.com/forge *Builder Resource Center, with demos, notebooks, and reference code:* https://www.coreweave.com/builder Thank you to Parag Agrawal, Dylan Patel, Jenson Button, and Sean Evans for joining us on stage. *Follow CoreWeave* X: https://x.com/CoreWeave LinkedIn: https://www.linkedin.com/company/coreweave Chapters 0:00 Brian Venturo: Built for Ambition 7:28 Jon Jones with Parag Agrawal, Parallel Web Systems 27:32 Chen Goldberg with Dylan Patel, SemiAnalysis 51:24 Jean English with Jenson Button: Realizing Ambition in Formula One 1:10:43 Mike Intrator on the Hot Seat with Sean Evans 1:46:37 Jean English closes Day 2 Built for AI. Fully Connected. #FullyConnected26
Recursive Self Improvement (RSI) of an AI Harness (Google)
Recursive Self-Improvement (RSI) of an AI harness complexity. Self-evolution of an AI harness. Recursive Agent Harnessing. all rights w/ authors: Harness Self-Evolution: Theory, Algorithms, Evaluation, Applications, and Impact Chuyang Wei1, Haoxiang Guan1, Minghang Zhu1, Kexin Zhou1, Jiyan He1,2, Yifei Shen1,2,† 1 Zhongguancun Academy 2 Zhongguancun Institute of Artificial Intelligence Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses Weichen Yu1 2 *, Lesly Miculicich1, Bhavana Dalvi Mishra1, Jiefeng Chen1, Shuo Li3, Matt Fredrikson2, Tomas Pfister1 and Long T. Le1 1 Google Cloud AI Research, 2 Carnegie Mellon University, 3 Google DeepMind Harness2: Recursive Agent Harnessing for an Open World Ruiyao Xu1*, Yanfei Chen2, Zhongying CuiZhu2, Bhavana Dalvi Mishra2, Yifei Ming2, Han Yu2, Rujun Han2, Chen-Yu Lee2 and Tomas Pfister2 1 Northwestern University, 2 Google Cloud AI Research #airesearch #aitechnology #aitech #aiexplained #discoverai
Multiplayer Gaming & Flight Simulation - Computerphile
Using the example of a flight simulator to discuss the complexities of coding a multi-player game. What data do you send? When do you send it & how often? Dr Julian Onions talks about his experiences of working on a flight simulator. Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: https://jane-st.co/computerphile This video was filmed and edited by Sean Riley. Computerphile is a sister project to Brady Haran's Numberphile. More at https://www.bradyharanblog.com
How Stripe Built Kai
What if everyone had an always-on, production-ready assistant? At Stripe, their answer was a company-wide AI agent called Knowledge AI Platform, also known as Kai. In less than 2 minutes, learn how Stripe built Kai in just 1 week using Deep Agents, LangChain's open-source agent harness. Deep Agents provides the foundation that wires together the tool-calling loop, middleware composition, streaming, and state management that would otherwise take months to build and harden from scratch. Learn more: Blog (10 min read) → https://www.langchain.com/blog/how-stripe-built-their-knowledge-ai-platform-on-deep-agents Introduction to Deep Agents (Free course) → https://academy.langchain.com/courses/foundation-introduction-to-deepagents Intro to Deep Agents Virtual Workshop (Recording) → https://events.langchain.com/intro-to-deep-agents-101/ Intro to Deep Agents Live Workshop (Register) → https://events.langchain.com/register/apac-anz-agent-harnesses-and-deep-agents-workshop/
Give your agent a goal, and let it be creative
Learn how to use verification and continuous improvement to make your AI agents better over time. In this video, I walk through building a custom video editor and using a scorecard system to track performance metrics, then having agents autonomously work to improve them day after day. Keep up to date with my skills here: https://aihero.dev/s/l2LvvX Follow Matt on Twitter https://twitter.com/mattpocockuk Join the Discord: https://aihero.dev/s/9uhQZL
IntelliJ IDEA’s Java and Kotlin for Cursor and VS Code Hits 1.0
Ten weeks ago, we opened up a preview of an LSP-powered extension that brings IntelliJ IDEA’s smartness for Java and Kotlin into VS Code and Cursor. As mentioned in that blog post, this is part of a bigger initiative: moving our JVM intelligence to wherever our users are, no matter what editor or agent they
Why You Think the Frontier Model Is Always Better (It's Psychology)
Eno Reyes, CTO of Factory, argues that once people know which model they're using, their preferences fly toward frontier models regardless of actual performance — and that this psychological bias, not raw capability, explains a lot of the last few months in AI. At enterprise scale, he says, the cost math will eventually win out over the brand name. From the Max Agency podcast, hosted by Harrison Chase, Co-Founder and CEO of LangChain. #AI #OpenSourceAI #FactoryAI #AIagents
The Best Place to Become a Data Analyst in 2026
Check out our Career Roadmaps Here: https://analystbuilder.com/roadmaps Get 30% off any purchase using code "30OFF" at checkout! Technical/General Questions: https://analystbuilder.com/questions?type=technical Projects: https://analystbuilder.com/projects ____________________________________________ RESOURCES: 💻Analyst Builder - https://www.analystbuilder.com/ 📖Take my Full MySQL Course Here: https://bit.ly/3tqOipr 📖Take my Full Python Course Here: https://bit.ly/48O581R 📖Practice Technical Interview Questions: https://bit.ly/46pDqqL 📖Beyond the Interview Book: https://www.amazon.com/Beyond-Interview-Building-Your-Career/dp/B0H6336726/ref=tmm_pap_swatch_0 Coursera Courses: Google Data Analyst Certification: https://coursera.pxf.io/5bBd62 Data Analysis with Python - https://coursera.pxf.io/BXY3Wy IBM Data Analysis Specialization - https://coursera.pxf.io/AoYOdR Tableau Data Visualization - https://coursera.pxf.io/MXYqaN *Please note I may earn a small commission for any purchase through these links - Thanks for supporting the channel!* ____________________________________________ BECOME A MEMBER - Want to support the channel? Consider becoming a member! I do Monthly Livestreams and you get some awesome Emoji's to use in chat and comments! https://www.youtube.com/channel/UC7cs8q-gJRlGwj4A8OmCmXg/join ____________________________________________ Websites: 💻Website: AlexTheAnalyst.com 💾GitHub: https://github.com/AlexTheAnalyst 📱Instagram: @Alex_The_Analyst ____________________________________________ *All opinions or statements in this video are my own and do not reflect the opinion of the company I work for or have ever worked for*
The Jevolution, Explained: What Jev Actually Is and Why Everyone Is Trying to Copy It
What is Jev? TypeSafe’s Jev is a new kind of AI model, a “decision model,” that doesn’t write text. It makes fast, cheap, calibrated decisions inside software, and it has taken the AI world by storm: within weeks of launch it became the most copied model in AI, with OpenAI, Cloudflare, Amazon and Databricks all shipping their own versions, and TypeSafe just raised an $870 million Series A at a $7.5 billion valuation. In this episode, Jev’s creator Diogo Almeida, co-inventor of RLHF at OpenAI and now CEO of TypeSafe, explains Jev in plain English: what a “System One” or decision model actually is, why ChatGPT-style language models can’t be trusted inside software (“95% Einstein, 5% Mr. Bean”), how RLHF and RLVR created the problem, what RLCD (reinforcement learning for calibrated decisions) does differently, where the training data comes from, which models Jev is built on, why “just a classifier” is a compliment, and why he calls pre-training “a giant dumpster fire of wasting resources.” We also cover the copycats and why he thinks they missed the hard part, why benchmarks are useless, whether Jev will go open source, the Jevons paradox business model behind the name, why he doesn’t believe AI is on the path to recursive self-improvement, and why he thinks the AI winter he feared has been averted. Diogo Almeida LinkedIn — https://www.linkedin.com/in/diogomda X — https://x.com/CompleteSkeptic TypeSafe AI Website — https://typesafe.ai X — https://x.com/typesafeai Matt Turck (General Partner) Blog - https://mattturck.com LinkedIn - https://www.linkedin.com/in/turck/ X - https://x.com/mattturck FirstMark Capital Website - https://firstmark.com X - https://x.com/FirstMarkCap Listen on: Spotify - https://open.spotify.com/show/7yLATDSaFvgJG80ACcRJtq Apple - https://podcasts.apple.com/us/podcast/the-mad-podcast-with-matt-turck/id168623872 00:00 Cold open & Intro: “95% Einstein, 5% Mr. Bean” 01:09 Jev’s breakout launch: why intelligence per dollar matters 03:25 Why Typ
This Founder Raised $112M to Build Retail AI That Sells Like TikTok
In this episode, Zoe Weil, co-founder and CEO of Sequen, joins us to discuss how ranking systems can use live behavioral signals to optimize for purchases rather than clicks or search relevance alone. Zoe explains why approaches developed at data-rich social platforms don’t necessarily translate to retailers and how Sequen uses scroll speed, hover duration, and other in-session interactions to infer shopper intent without relying on user identity. We explore the company’s large event models and its architecture of specialized models that transform streaming events into features for downstream rankers. Zoe describes the infrastructure required to serve dynamic rankings within milliseconds, why the team chose Rust for its backend, and how evaluation harnesses connect model improvements to business outcomes. We also discuss the tradeoffs between advertising and organic revenue, continuous model improvement, and the boundary between useful personalization and surveillance. Full show notes including references: https://twimlai.com/go/780. 🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confirmation=1 📖 CHAPTERS =============================== 00:00 - Introduction 02:56 - Sequin’s Ranking Intelligence Layer 07:26 - Difference with Search and Relevance 13:20 - Session Live Signaling 15:57 - Surveillance Capitalism 18:45 - Building a Low-Latency Stack in Rust 20:52 - Model Architecture 26:47 - Reranking Products and Surfacing Complementary Items 33:03 - Balancing Organic and Ad Revenue 34:56 - Learning from Implicit Feedback 36:42 - Infrastructure 39:34 - Recursive Stack and Evaluation Harnesses 42:31 - Recursive Ranking Intelligence 44:12 - Large Event Models 46:56 - Time-Series Modeling 48:49 - Complexity of Scaling Real-Time Feature Transformations 49:46 - Future Directions 🗣️ CONNECT WITH US! =============================== Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/ Follow us on Twitt
Revolutionizing Cybersecurity and AI-Driven Science with OpenAI President Greg Brockman
Technology has always been the fundamental driver of improvement for human quality of life. And with the recent rollout of advanced frontier models, like OpenAI’s GPT-6, humanity can now massively accelerate scientific discovery for its benefit. Sarah Guo and Elad Gil are joined by OpenAI President and co-founder Greg Brockman to discuss the company’s rapid progress across frontier models, cybersecurity, and scientific discovery. Greg shares how nearly 400 century-old math problems have been solved using its AI agents, and how the technology has the potential to transform other fields like biology in the realm of drug discovery. He also talks about how proactive, always-on AI agents like Dots impact modern productivity, why he believes the best UI is no UI at all, how cybersecurity is in a critical window of time to use peak intelligence to find and fix vulnerabilities in systems, and why OpenAI remains committed to keeping humans in the driver’s seat even as models surpass us in capability. Sign up for new podcasts every week. Email feedback to show@no-priors.com Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @gdb | @OpenAI Chapters: 00:42 – Trailer 00:59 – Greg Brockman Introduction 01:11 – AI and Advancements in Mathematics 05:55 – AI Communication and Oversight 07:45 – AI for Overcoming Biology Data Bottlenecks 11:28 – Revolutionizing Drug Discovery 14:18 – Changing Regulations to Accelerate Progress 16:51 – Dots the Proactive Agent 19:19 – Unifying Work and Consumer Agents 22:02 – How UI Will Evolve 26:08 – Cybersecurity in the AI Age 32:55 – Shift in Security Investment 35:49 – OpenAI’s Human-Centric Ethos 38:28 – Conclusion
Ep. 246: AI Answers - Live from MAICON 2026: AGI, AI Costs, and the End of GPTs
Live from the podcast studio at MAICON 2026, Paul Roetzer and Mike Kaput answer questions submitted by the audience in the room, an unfiltered AI Answers episode on the direction AI is actually heading. Mike and Paul cover topics including whether we already have AGI, why frontier model costs keep falling, building an AI roadmap you can stick to as models change monthly, what to do now that GPTs are going away, and who legally owns the AI work you create at work. 00:00:00 — Intro 00:04:03 What MAICON insight has challenged your thinking about where AI is headed? 00:07:46 How do you keep up with AI without burning out? 00:12:09 How do you go from following a demo to using AI in your own work? 00:15:21 How do you get AI adopted in the messy middle of an organization? 00:17:41 How do you build an AI roadmap you can stick to as models change? 00:22:09 Will Claude and ChatGPT get more expensive after the IPOs? 00:26:23 What can AI do versus what should AI do? 00:30:35 What does AGI actually look like for a regular person? 00:35:25 Can AI solve the unemployment it creates? 00:39:42 Can you take your AI work with you from job to job? 00:41:19 Do you have to readjust when you switch AI models at a new job? 00:44:08 What should you use now that GPTs are going away? 00:46:42 Closing thoughts and a look ahead to MAICON 2027 Access the show notes and show links here: https://podcast.smarterx.ai/shownotes/246?utm_source=youtube&utm_medium=social&utm_campaign=podcast_shownotes Want to receive our videos faster? SUBSCRIBE to our channel! ✅ Subscribe for more episodes: https://www.youtube.com/@aishowpod 📬 Get our weekly newsletter: https://www.marketingaiinstitute.com/newsletter 🎓 Enroll in AI Academy: https://academy.smarterx.ai/ 🎤 Join us at MAICON: https://www.MAICON.ai 📺 Register for a free webinar: https://smarterx.ai/webinars Connect with us 💬 Slack community: https://smarterx.ai/community 💼 LinkedIn: https://www.linkedin.com/company/smarterxai 🐦 X/Twitter: https
FABLE 5.5 THIS WEEK? OpenAI Employee ARRESTED?! HUGE Claude Code Update, & Anthropic IPO! AI NEWS
Build 3D games and apps with Astra and Opus 5.5 on Abacus AI SuperComputer!: https://supercomputer.abacus.ai/ Anthropic's mysterious Claude Fable 5.5 has been spotted once again in Microsoft's Azure infrastructure, with new evidence suggesting the next-generation AI model could launch very soon! Meanwhile, OpenAI is facing a bizarre security scandal after a former employee was arrested for allegedly planting a hidden recording device inside an executive conference room. 🤯 🚨 Everything you’re about to see, I benchmarked using the tool I made. If you want to run these tests yourself or test models on whatever you actually use them for! → https://www.woaibench.ai/ Join the private community to get WoAI Bench Pro, exclusive AI freebies and discounts, early model access, automation templates, practical resources and upcoming AI training. 👉 Join Today! https://www.skool.com/worldofai 🔗 My Links: Sponsor a Video or Do a Demo of Your Product, Contact me: intheworldzofai@gmail.com 🔥 Become a Patron (Private Discord): https://patreon.com/WorldofAi 🧠 Follow me on Twitter: https://twitter.com/intheworldofai 🚨 Subscribe To The SECOND Channel: https://www.youtube.com/@UCYwLV1gDwzGbg7jXQ52bVnQ 👩🏻🏫 Learn to code with Scrimba – from fullstack to AI https://scrimba.com/?via=worldofai (20% OFF) 🚨 Subscribe To The FREE AI Newsletter For Regular AI Updates: https://intheworldofai.com/ 👾 Join the World of AI Discord! : https://discord.gg/NPf8FCn4cD [Must Watch]: Meta's Muse Wonder IS OPUS 5.5 LEVEL?! I Don't Think So... (Fully Tested): https://youtu.be/f7OpKLA-CLI Gemini 4 Argon Is Out, Fable 5.5 This Week? GPT-6.1 Astra, Nano Banana 3 & AI Self-Creating! AI NEWS: https://youtu.be/bk1xyTwzsY8 Claude Opus 6 LEAKED, Gemini 4 Carbon Leaks, HUGE OpenAI Update, Claude 24/7 Agent, & More! AI NEWS: https://youtu.be/4iKUaUmeoWk 📌 LINKS & RESOURCES World of AI Skool: https://www.skool.com/worldofai World of AI Benchmark: https://www.woaibench.ai/ AI NEWS: https://x.com/inthewo
AI just BROKE all of the software industry
Minecraft in GTA. Mario in Elden Ring. And software companies suddenly competing with their own customers. AI is changing how people modify games and rebuild the tools they use, so I tried it myself. Here's what people are making, how to get started, and why some of the possibilities get uncomfortable fast. ______________________________________________ My Links 🔗 ➡️ Twitter: https://x.com/WesRothMoney ➡️ AI Newsletter: https://natural20.beehiiv.com/subscribe Want to work with me? Brand, sponsorship & business inquiries: wesroth@smoothmedia.co ______________________________________________ SOURCES: Mario in Elden Ring: https://github.com/deltarooo/er-mario Minecraft in GTA V: https://github.com/rehan-remade/universal-modder/blob/main/examples/minecraft-gta5-passthrough/README.md SRE-Bench research paper: https://arxiv.org/html/2608.11469v2 PhotoCraft, open-source image editor: https://github.com/storytold/photocraft FilmCraft, open-source video editor: https://github.com/storytold/filmcraft Nigel, iterative coding-agent workflow: https://github.com/cdlewis/nigel Snowboard Kids decompilation: https://github.com/cdlewis/snowboardkids-decomp Reverse Engineer Anything: https://github.com/morluto/rea ArkWeb, Spider-Man movement in Batman: https://github.com/luki-1/ArkWeb Universal Modder: https://github.com/rehan-remade/universal-modder CHAPTERS: 00:00 Game Mashups 03:00 Reverse Engineering 06:00 Building Software 09:00 Adobe Alternatives 12:00 Game Exploits 17:00 Training Data 19:00 Modding Tools 25:00 Personal Projects #ai #gaming #codex
Gemini 4 Argon cost a third of Opus 5.5 on my own podcasts
Google lists Gemini 4 Argon at half the price of Claude Opus 5.5. I ran both, plus GPT-6 Astra, on 20 of my own podcast excerpts with the same prompt and default settings. Argon cost a third of Opus on this job. Comment ARGON and I'll send you the sheet. More on Substack: https://aibyaakash.com Sources (read Oct 14 2026): Gemini API pricing: https://ai.google.dev/gemini-api/docs/pricing Claude pricing: https://platform.claude.com/docs/en/about-claude/pricing OpenAI pricing: https://platform.openai.com/docs/pricing
Showing 20 of 200 videos
Know a source we’re missing? Tell us about it