List from buildsoftwarewithai.com
AI for Developers
Tools, techniques and ideas for building software with AI.
Latest videos
Newest first
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
Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
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
How You Need to Think About Product Strategy in the Age of AI
AI has made shipping features cheap, which makes choosing the wrong ones more expensive than ever. Tim Herbig, product strategy coach and author of Real Progress, walks through how to build a product strategy that actually helps you say no. Full write-up: https://www.news.aakashg.com/p/how-the-best-pms-think-about-product-strategy Transcript: https://www.aakashg.com/product-strategy-in-the-age-of-ai-with-tim-herbig/ Timestamps 03:06 - Cheap features make wrong choices expensive 05:33 - The one test every strategy has to pass 07:19 - Ads 09:02 - The core questions every strategy answers 12:39 - Why AI is not a value proposition 18:41 - The Roger Martin test and the stupidity flip 25:11 - Ads 30:59 - Case study - Fair Mile, a used car marketplace 35:43 - Audience trees 42:16 - Differentiation with the 7 Powers 52:48 - How to know if your strategy worked 58:30 - Building the strategy and metrics loop 1:04:33 - What you inherit vs. what you create 🏆 Thanks to our sponsors 1. Fingerprint: Identify good and bad visitors with industry-leading accuracy - https://tinyurl.com/2s3p65p7 2. Ariso: Ship AI agents and features faster, with fewer regressions - https://ariso.ai/aakash 3. Customer.io: Send smarter messages using your product data - http://customer.io/productgrowth 4. Amplitude: The market leader in product analytics - https://tinyurl.com/b7nret7v 5. Product Faculty: Get $150 off their #1 AI PM Certification via code AAKASH150 - https://www.productfaculty.com/?code=AAKASH150 Key Takeaways 1. Cheap features make wrong bets expensive - AI made shipping fast, so picking the wrong feature now costs more, not less. You still have to get people to use everything you ship. The real question is whether any of that output moved customers and the business. 2. A strategy is only real if it helps you say no - Deck, one-pager, or framework, the test is the same. If it doesn't help teams say no to opportunities, it isn't a strategy. A healthy one has most of your team's en
CoreWeave Fully Connected 2026 Keynote: Introducing CoreWeave Forge | Built for Adoption
CoreWeave Fully Connected 2026 Day 1 keynote: the launch of CoreWeave Forge, live demos of agentic AI in production, and the NVIDIA Vera Rubin NVL72. Getting to production is the starting line, not the finish. Deploying an AI agent is step one. Keeping it performing takes a tight, continuous loop between inference, data curation, and model evaluation. In our Day 1 Keynote, Built for Adoption, we show what sets CoreWeave Cloud apart for teams running AI in production. Watch live demos of evaluating, distilling, and rolling out models in one environment, plus a CoreWeave Mission Control agent finding and fixing a live inference failure on stage. NVIDIA debuts the Vera CPU and Vera Rubin NVL72, and engineering leaders from Cognition, Caterpillar, and Capital One share what they’re seeing in production. *Learn more about CoreWeave Forge:* https://docs.coreweave.com/forge *Corey's full Forge demo, on its own:* https://www.youtube.com/watch?v=Q7UwZjEVFWA *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 *Fully Connected 2026, all sessions:* https://www.coreweave.com/fully-conne... Chapters: 0:00 Opening Video 0:49 Brian Venturo: Welcome to Fully Connected 7:30 Chen Goldberg: There's Never Been a Better Time to Be an Engineer 13:26 Brandon Hutman: Caterpillar on Physical AI & Autonomy 18:59 The Complexity of Agents & the AI Loop 23:29 Announcing CoreWeave Forge 34:26 Ian Buck: NVIDIA Vera Rubin & Six GPU Generations 48:04 Corey Sanders: Observe, Curate & Improve: Agent Lens, Distillation, RL Rollout 53:33 Maulin Patel: Capital One on Evaluating AI Agents 1:04:07 Live Demo: The Full AI Loop in Forge 1:16:28 Silas Alberti: Cognition on Vera Rubin 1:28:35 CoreWeave Origin Story – Corey Sanders & Mike Intrator 1:49:19 Brian Venturo: Closing Remarks
Give your team AI skills you can trust
Learn more: deeplearning.ai/business Our enterprise program gives your team AI skills you can trust. Engineering teams are under pressure to build AI skills. In BCG's 2026 survey, 72% of workers said AI has changed what their jobs require. Only 36% felt adequately upskilled. Our program helps close that gap. We analyzed more than 10,000 job roles and interviewed dozens of leading AI engineering experts to identify the skills that matter most. Those who learn through our enterprise program are five times more likely to keep learning over time than those learning on their own. See how our program could work for your team: deeplearning.ai/business
GPT-6 Didn't Stop Flattering You. It Got Better at Hiding It
WORK WITH ME 📲 25-Min AI Strategy Call (Biz Owners/Leaders): https://go.gradientlabs.co/gpt-6-didnt-stop-flattering-you-it-got-better-at-hiding-it/strategy 💪 AI Coaching: https://go.gradientlabs.co/gpt-6-didnt-stop-flattering-you-it-got-better-at-hiding-it/coaching FREE STUFF 💌 30-Day AI Insights: https://go.gradientlabs.co/gpt-6-didnt-stop-flattering-you-it-got-better-at-hiding-it/insights SOCIALS LinkedIn: https://www.linkedin.com/in/dylantdavis/ RESOURCES Presentation (with prompts): https://d-squared70.github.io/GPT-6-Didnt-Stop-Flattering-You-It-Got-Better-at-Hiding-It/
Cooking up a catering business with ChatGPT
Running a restaurant is a 24/7 commitment. And apparently finding catering clients is just as time-consuming. Nick Baumann visited Richard at @thedumplingprince in Toronto to put ChatGPT to work on a catering deck and automated outreach. It didn't get an apron. 👉🛠️ Wish something existed? Drop your idea below or DM us and we'll come build it with you next.
The Rule of Three for Coding Agents
The middle loop in agent feedback loops exists because of the rule of three. Maria Gorinova explains why the agent writing the same code a third time isn't the one that should notice, and what has to sit above it to catch the drift. Watch the full episode at https://youtu.be/wrRxw15s31k or listen wherever you get your podcasts
Why Atlassian Is Hiring More Juniors in the AI Era
Atlassian flipped its hiring pipeline. "We're now hiring a lot more on the junior end... and it's worked wonders for us." Juniors are 2x as likely to experiment with AI, says Sherif Mansour. The unlearning problem is the seniors', not the juniors'.
Claude Projects Run Your Business (Exact Setup)
Save 10+ hours per week with Claude: https://aifoundations.io/go/c-suite-6 Learn how to set up Claude Projects to run real work in your business. This Claude Projects tutorial covers the new coordinator agent and threads, how to create a Claude Project with a clear goal, what business context to add (your business overview, priorities, voice and past work), how project memory and project instructions work, and how to put recurring tasks on a schedule with Claude routines. If you want to use Claude for business automation and stop managing every AI task yourself, this is the exact Claude Projects setup I use at AI Foundations. -------------------- ⌚Chapters: 0:00 - Claude Projects Run Your Business 0:54 - Step 1: Pick the Job 1:55 - Creating a Claude Project 2:53 - Writing the Project Goal 3:22 - Coordinator Agent and Threads 5:07 - Step 2: Adding Context 7:03 - Business Overview and Priorities 8:36 - Newsletter Context Files 10:28 - Past Email Campaigns as Context 11:23 - Step 3: Work With Claude 13:27 - Project Memory and Instructions 14:01 - Threads Working in Parallel 15:26 - Filling the Context Gaps 17:57 - The Automated C-Suite Course 18:56 - Drafting a Newsletter With Claude 20:37 - Reviewing the Newsletter Draft 23:15 - Reminders in Claude Projects 23:51 - Step 4: Put It on a Schedule 24:56 - Creating a Claude Routine 26:43 - The Saturday Newsletter Routine 27:34 - Routine Trigger and Instructions 29:22 - Final Thoughts #claude #claudeprojects
Meta's Muse: best AI agent, worst designer
Claire tested Meta's Muse across 8 categories. It ranked 1st on agents and coding, but tied for 7th on creative work like video editing, where Opus 5.5 still wins. Full episode of How I AI with Claire Vo is out now.
How Hugging Face’s Investor Spots Winners
Check out Gemini Audio: https://goo.gle/Every-Gemini-Audio Bet on founders who understand the technology, because their first idea probably won’t be the one that sticks. That’s the view of Matt Hartman, founder and managing partner of Factorial Capital. In 2016, as a partner at Betaworks, Hartman was part of the team that wrote the first check into Hugging Face, which was then a chatbot app for teenagers. Today it’s the largest hub for open-source AI, and Nvidia has agreed to buy it for about $13 billion. On this week’s episode of The Every Podcast, Hartman tells Natalia Quintero how backing Hugging Face shaped his investment thesis, how Factorial grew into a “family tree” of technical founders who help him scout deals, and why vibe-coding his own app gave him a new respect for SaaS. Subscribe to Every (free for 14 days): https://every.to/podcast-every-offer?utm_source=podcast&utm_medium=audio&utm_campaign=matthartmanepisode Links to resources mentioned in the episode: Factorial Capital: https://factorialcap.com Ghost Pepper, Matt's open-source voice-to-text app: https://github.com/matthartman/ghost-pepper Superpowers, Jesse Vincent's skill for Claude Code: https://github.com/obra/superpowers Hugging Face: https://huggingface.co Follow Every: https://x.com/every Follow Natalia Quintero: https://x.com/NataliaZarina Follow Matt Hartman: https://x.com/MattHartman 0:00 Introduction 5:06 How Hugging Face went from a teen chatbot to the home of open-source AI 9:52 The three decisions that set Hugging Face on its path 12:49 Hartman’s approach to finding the newly technically possible 18:10 Why Hartman backs technical founders 21:10 How Factorial’s portfolio founders source its next deals 27:09 Why faster iteration makes product insight the most valuable skill 34:28 What Hartman learned building Ghost Pepper, an open-source voice-to-text app 40:02 Hartman’s current theses, from non-language models to full-stack AI apps 44:14 Why the best founders right now are
From extraction to action: Using grounding and confidence to build reliable document workflows
Learn how Azure Content Understanding grounding, field-level confidence, and calibration help teams prioritize human review and build reliable document workflows.
What is Deep Agents?
Deep Agents is LangChain's open source agent harness built for long-running tasks. It handles planning, context management, and multi-agent orchestration for complex work like research and coding. Learn more about Deep Agents: LangChain Academy → https://academy.langchain.com/courses/foundation-introduction-to-deepagents Docs → https://docs.langchain.com/oss/python/deepagents/overview 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/
Voice Standard Bench - which LLM is best for transcripts?
Which LLM should you run your transcripts on? There are leaderboards for coding, math, and trivia, but none of them test what an LLM actually does inside a voice product like a meeting transcriber or dictation app. Voice Standard Bench gives every model on AssemblyAI's LLM gateway the same transcripts, from a 30-second voicemail to an hour-long meeting, and tests them on information extraction, summarization, and text cleanup. An independent LLM scores every answer, and quality, speed, and cost are compared side by side. Read more about Voice Standard Bench here: https://www.assemblyai.com/blog/voice-standard-bench Run the bench on your own audio → https://github.com/AssemblyAI/voice-standard-bench ▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬ 🖥️ Website: https://www.assemblyai.com 🐦 Twitter: https://twitter.com/AssemblyAI 🦾 Discord: https://discord.gg/Cd8MyVJAXd ▶️ Subscribe: https://www.youtube.com/c/AssemblyAI?sub_confirmation=1 🔥 We're hiring! Check our open roles: https://www.assemblyai.com/careers ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ #MachineLearning #DeepLearning LLM benchmark, best LLM for transcripts, voice AI, LLM gateway, transcript summarization, meeting transcription, AI models, open source benchmark, speech-to-text, AssemblyAI
Showing 20 of 200 videos
Know a source we’re missing? Tell us about it