[{"channel_id":1634145994,"post_id":1810,"date":1781010107000,"views":"10","text":"Run local agentic AI on the Mac using MLX \ud83d\ude80<br><br>Apple Developer released a new WWDC26 session yesterday on running local agentic AI on the Mac using MLX \u2014 privacy, low latency, and offline access, entirely on-device.<br><br>This 14-minute session covers the following topics:<br>\u2705 The chat and agentic loop<br>\u2705 Local agentic AI stack<br>\u2705 Setting up your own agent<br>\u2705 Making agents fast<br>\u2705 Concurrency and distributed inference<br><br>\ud83d\udcfd\ufe0f: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=wykPErJ8M-8\">https:\/\/www.youtube.com\/watch?v=wykPErJ8M-8<\/a>","text_length":459,"media":{"root":"\/00b\/EgcAAMoWZ2EAAAAAgz_tAKfx_ck","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=wykPErJ8M-8","type":"video","title":"WWDC26: Run local agentic AI on the Mac using MLX | Apple","site_name":"YouTube","display_url":"youtube.com\/watch?v=wykPErJ8M-8","description":"Run AI agents locally with privacy, low latency, and offline access. Dive into how MLX advancements and Mac hardware make powerful agentic workflows possible entirely on-device. You\u2019ll explore code agents such as OpenCode, see how they integrate into Xcode, learn techniques for multi-Mac scaling, and discover how to integrate tools seamlessly \u2014 without ever leaving your machine.\n\nExplore related documentation, sample code, and more:\nMLX Swift LM on GitHub: https:\/\/github.com\/ml-explore\/mlx-swift-lm\nMLX Swift: https:\/\/github.com\/ml-explore\/mlx-swift\nMLX  LM - Python API: https:\/\/github.com\/ml-explore\/mlx-lm\nMLX Explore - Python API: https:\/\/github.com\/ml-explore\/mlx\nMLX Framework: https:\/\/mlx-framework.org\nMLX: https:\/\/ml-explore.github.io\/mlx\/\nMLX Swift Examples: https:\/\/github.com\/ml-explore\/mlx-swift-examples\nMLX Examples: https:\/\/github.com\/ml-explore\/mlx-examples\nExplore distributed inference and training with MLX: https:\/\/developer.apple.com\/videos\/play\/wwdc2026\/233\nExplore numerical computing in Swift with MLX: https:\/\/developer.apple.com\/videos\/play\/wwdc2026\/328\nBuild local AI agents on Mac with MLX: https:\/\/developer.apple.com\/videos\/play\/wwdc2026-shorts\/229\nGet started with MLX for Apple silicon: https:\/\/developer.apple.com\/videos\/play\/wwdc2025\/315\nExplore large language models on Apple silicon with MLX: https:\/\/developer.apple.com\/videos\/play\/wwdc2025\/298\n\n00:00 - Introduction\n00:32 - The chat and agentic loop\n02:42 - Local agentic AI stack\n04:36 - Setting up your own agent\n05:39 - Making agents fast\n06:53 - Concurrency and distributed inference\n09:20 - More examples\n13:01 - Next steps\n\nMore Apple Developer resources:\nVideo sessions: https:\/\/apple.co\/VideoSessions\nDocumentation: https:\/\/apple.co\/DeveloperDocs\nForums: https:\/\/apple.co\/DeveloperForums\nApp: https:\/\/apple.co\/DeveloperApp","thumbs":{"m":{"w":320,"h":180,"hash":"bE2CTFD9BGMUzVoym8fd2g&ts=1781078627"},"x":{"w":800,"h":450,"hash":"IKt2pmqEnCXOvGkIPAePug&ts=1781078627"},"y":{"w":1280,"h":720,"hash":"YapB3YPe3QUl0cuCvCE5vw&ts=1781078627"},"i":{"bytes":"AXACg|CvCy+aMZq2TTVjXAO4D8KVgMH5wKdxWsUdqkSE5yCaiAq1s25\/eDPfioyinJD549O9JoFK5FiinyKExhs\/hRUjLZmVF+aRh7YqM3O7iN2OfWiiqGNKyu2S2R1IJqRB8oFFFJsLakcluzsWDD6UUUUhn\/\/Z"}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/wykPErJ8M-8","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1809,"date":1780996476000,"forwards":"1","views":"35","text":"PaperBanana \ud83d\ude80<br><br>An open-source agentic framework for generating publication-quality academic diagrams and statistical plots from text descriptions.<br><br>A multi-agent pipeline drafts a figure and refines it over several rounds with a critic agent.<br><br>Works with OpenAI, Azure, Gemini (free tier), and OpenRouter. CLI, Python API, and MCP server included. Batch generation, composite figures, and VLM-as-a-Judge evaluation built in.<br><br>MIT-licensed.<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/github.com\/llmsresearch\/paperbanana\">https:\/\/github.com\/llmsresearch\/paperbanana<\/a>","text_length":485,"media":{"root":"\/013\/EQcAAMoWZ2EAAAAAJC97GOG_yXw","webpage":{"url":"https:\/\/github.com\/llmsresearch\/paperbanana","type":"photo","title":"GitHub - llmsresearch\/paperbanana: Open source implementation and extension of Google Research\u2019s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.","site_name":"GitHub","display_url":"github.com\/llmsresearch\/paperbanana","description":"Open source implementation and extension of Google Research\u2019s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation. - llmsresear...","thumbs":{"m":{"w":320,"h":158,"hash":"P6dsI_kLrsJKobF61ZD2WQ&ts=1781078627"},"x":{"w":800,"h":396,"hash":"iisiLs2CEWmqvWY9dxmXUQ&ts=1781078627"},"y":{"w":1280,"h":633,"hash":"h8z4T0IABakPPFXxrCTAfw&ts=1781078627"},"w":{"w":2560,"h":1266,"hash":"bTgsQF3LAt59i1dQTu2rzQ&ts=1781078627"},"i":{"bytes":"AUACg|DVYPuOHIHpxSBZOP3h\/T\/ClZ2DEClVyTgigB2fWjcAetIwJA7YqFh85z6YpATgg9KKjiT5VOaKAJcUYoopgFFFFABRRRQB\/9k="}}}}},{"channel_id":1634145994,"post_id":1808,"date":1780786548000,"views":"31","text":"My weekly newsletter is out! \ud83d\uddde\ufe0f<br><br>This week&#039;s agenda:<br>\ud83d\udd39 Open Source of the Week - The Promptolian project by Maurizio Lospinoso<br>\ud83d\udd39 New learning resources - Stanford CS25 Transformers, Docker for DevOps, Pi Agent, PostgreSQL crash course, 9 AI concepts<br>\ud83d\udd39 Book of the week - Mastering Tableau 2026 by Marleen M.<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/p\/the-promptolian-project-stanford\">https:\/\/ramikrispin.substack.com\/p\/the-promptolian-project-stanford<\/a>","text_length":380,"media":{"root":"\/003\/EAcAAMoWZ2EAAAAAvwDoUbFJeyY","webpage":{"url":"https:\/\/ramikrispin.substack.com\/p\/the-promptolian-project-stanford","type":"photo","title":"The Promptolian Project, Stanford CS25 Transformers, Mastering Tableau 2026 | Issue 91","site_name":"Substack","display_url":"ramikrispin.substack.com\/p\/the-promptolian-project-stanford","description":"A weekly curated update on data science and engineering topics and resources.","thumbs":{"m":{"w":320,"h":160,"hash":"wtyIaskO30Wx758cKQjJ1g&ts=1781078627"},"x":{"w":800,"h":400,"hash":"jt5x9Ebixy8SL1LfAjTiKg&ts=1781078627"},"y":{"w":1280,"h":640,"hash":"yI6q1OViuz9R18Wisa-UzQ&ts=1781078627"},"w":{"w":1600,"h":800,"hash":"TNyTNmrxP7lBNJkcnFpRPg&ts=1781078627"},"i":{"bytes":"AUACg|CJXHcU8LnpTAtOJIGB1q7ka7MarmNsSjAPQ1YjwwypBFVW5hIfBf1NPtwqqM78eucVFy+UuDNFIJFFFLmDlM0O2OtKHY9+ooooNBNxOc+lLkjgfSiigADsQTmiiigD\/9k="}}}}},{"channel_id":1634145994,"post_id":1807,"date":1780576013000,"forwards":"2","views":"24","text":"Stanford CS25: Transformers \ud83d\ude80<br><br>Stanford Online&#039;s CS25 playlist on YouTube collects the seminar series on Transformers, including the latest season (V6) with seven new lectures plus prior seasons going back to V1.<br><br>The V6 series covers the following topics:<br>  \u2705 Overview of transformers<br>  \u2705 Representation learning to world modeling<br>  \u2705 State space models vs transformers<br>  \u2705 Scaling training across thousands of GPUs<br>  \u2705 Next-token prediction to next-generation intelligence<br>  \u2705 Generalization from parameters and context<br>  \u2705 Collaborative AI agents in science<br><br>\ud83d\udcfd\ufe0f: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/playlist?list=PLoROMvodv4rPZxxeUFvQHCkZJsaEBdDZj\">https:\/\/www.youtube.com\/playlist?list=PLoROMvodv4rPZxxeUFvQHCkZJsaEBdDZj<\/a><br><br>\u267b\ufe0f Please share if you find it useful","text_length":679,"media":{"root":"\/011\/DwcAAMoWZ2EAAAAAc_VhVqkVMKU","photo":{"thumbs":{"m":{"w":320,"h":194,"hash":"iqXvviUriOdIK9ZhdbulfA&ts=1781078627"},"x":{"w":800,"h":485,"hash":"gFpxkxsRCHrM-XHt04lNXQ&ts=1781078627"},"y":{"w":1280,"h":776,"hash":"gNTx9j1v4wbnHh4XQhbDag&ts=1781078627"},"i":{"bytes":"AYACg|CJ8b02hQuOcigRoUJJjB34xj2qPzhtxsGfXJqSAkpkF87zwv0pAUGxuPP6UnHr+lObO4\/epvPoaYCH\/PFFKfx\/GigBd9XLTDQtlc8+uP8APaiikBTcYc8Dr6038BRRTAKKKKAP\/9k="}}}}},{"channel_id":1634145994,"post_id":1806,"date":1780329043000,"forwards":"1","views":"48","text":"Meanwhile, some updates in my newsletter:<br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/p\/the-ai-hedge-fund-project-data-science\">https:\/\/ramikrispin.substack.com\/p\/the-ai-hedge-fund-project-data-science<\/a>","text_length":115,"media":{"root":"\/006\/DgcAAMoWZ2EAAAAAYzEd0sxmE0E","webpage":{"url":"https:\/\/ramikrispin.substack.com\/p\/the-ai-hedge-fund-project-data-science","type":"photo","title":"The AI Hedge Fund Project, Data Science First - New Book | Issue 90","site_name":"Substack","display_url":"ramikrispin.substack.com\/p\/the-ai-hedge-fund-project-data-science","description":"A weekly curated update on data science and engineering topics and resources.","thumbs":{"m":{"w":320,"h":160,"hash":"H5KFhcC5OMQHBoMQllPnww&ts=1781078627"},"x":{"w":800,"h":400,"hash":"4LLVoVhEcIWC_SKe5FsE3g&ts=1781078627"},"y":{"w":1280,"h":640,"hash":"5SgbJRCinVQ5bPC40LGcJw&ts=1781078627"},"w":{"w":1600,"h":800,"hash":"HDN8mtRlULKiinGB7tjkBg&ts=1781078627"},"i":{"bytes":"AUACg|C+ehqOMYY\/KR9aN6gdaZG67j1qXuhk9M\/eb8cY9cf\/AF6aCoPU0m9N\/wB6ndiFlOAPmYfQUVHO+QMBj9DRSY+S+pXLtjrTVds9TRRQ9wHb29aTcc570UVQgb5gc9qKKKYj\/9k="}}}}},{"channel_id":1634145994,"post_id":1805,"date":1780328998000,"views":"76","text":"Hi folks, the last two weeks were super intensive (course recording), did not have the chance to post here. This week, return to normal updates \ud83d\ude42","text_length":146},{"channel_id":1634145994,"post_id":1804,"date":1779751494000,"views":"56","text":"My weekely newsletter is out:<br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/p\/the-knowledge-work-plugins-project\">https:\/\/ramikrispin.substack.com\/p\/the-knowledge-work-plugins-project<\/a>","text_length":99,"media":{"root":"\/00b\/DAcAAMoWZ2EAAAAAgz_tAKfx_ck","webpage":{"url":"https:\/\/ramikrispin.substack.com\/p\/the-knowledge-work-plugins-project","type":"photo","title":"The Knowledge Work Plugins Project, Small Language Models - New Book| Issue 89","site_name":"Substack","display_url":"ramikrispin.substack.com\/p\/the-knowledge-work-plugins-project","description":"A weekly curated update on data science and engineering topics and resources.","thumbs":{"m":{"w":320,"h":160,"hash":"hB6a3RNeB3_cHwVGtCaJQw&ts=1781078627"},"x":{"w":800,"h":400,"hash":"f7dUAtfx0TntKoz2NOWruw&ts=1781078627"},"y":{"w":1280,"h":640,"hash":"NdMfIjO0eMj9Ym7NmTVCPQ&ts=1781078627"},"w":{"w":1600,"h":800,"hash":"FI_CPZ6pplig4ydbrmqAJg&ts=1781078627"},"i":{"bytes":"AUACg|DMhlfcqbsKTjpT5ZMvx06dKrqxRgw6ipHbpwASMmkO5LBKBgHBHuKmLRyZV0X2YCqRG0jByDQWPFAD5YghOOR60Ux23UUxDKsbAeT9KKKQ0JsG36ZpfLXOKKKBjGVRGTjmiiimJn\/\/2Q=="}}}}},{"channel_id":1634145994,"post_id":1803,"date":1779663053000,"forwards":"1","views":"42","text":"Code with Claude 2026 \ud83d\udc47\ud83c\udffc<br><br>All the talks from the Anthropic developer conference are now available to watch. This looks like an amazing resource for learning more about Claude Code directly from the development team. This includes discussion of prompt engineering best practices, working with agents, agentic workflows, and more.<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/playlist?list=PLmWCw1CzcFilPJdvw6scjHjbBripZWFps\">https:\/\/www.youtube.com\/playlist?list=PLmWCw1CzcFilPJdvw6scjHjbBripZWFps<\/a>","text_length":404,"media":{"root":"\/001\/CwcAAMoWZ2EAAAAAVk9ou28Qy0s","photo":{"thumbs":{"m":{"w":320,"h":254,"hash":"PZPDoPHfq5tFqfIkC7GHUQ&ts=1781078627"},"x":{"w":800,"h":634,"hash":"3rktR1E6nIUR0d_VtwYvTw&ts=1781078627"},"y":{"w":1280,"h":1015,"hash":"YHFIEZ8UWszF5oxlhyjGIg&ts=1781078627"},"i":{"bytes":"AgACg|CdIoCoyi5xUFzHEs0GEUgk5HHNLvfy8jy8Yz98f41WeQvJGMZ56CgRPeRItsxS3CnjnA4rLJPt+QrVvsG2PMhPHBBxWUQcfdoGJRSUUAWN1LG375CfWoN1S25JuEwcHPU0AaN+xNqQZVPTgDr+tZBrYvw4tW+RF6cg+\/0rIPXk0ANopaKAP\/\/Z"}}}}},{"channel_id":1634145994,"post_id":1802,"date":1779556735000,"forwards":"3","views":"77","text":"Hermes Agent Tutorial \ud83d\udc47<br><br>This short tutorial provides a step-by-step guide for setting up a Hermes agent. This includes agent installation, Telegram setup, adding skills, web scraping, MCP tools, etc.<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=6QZBep7mW0c\">https:\/\/www.youtube.com\/watch?v=6QZBep7mW0c<\/a>","text_length":246,"media":{"root":"\/002\/CgcAAMoWZ2EAAAAAhS9KIzvsUO4","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=6QZBep7mW0c","type":"video","title":"Hermes Agent Tutorial for Beginners - Crash Course","site_name":"YouTube","display_url":"youtube.com\/watch?v=6QZBep7mW0c","description":"Connect Hermes Agent to 9,000+ apps. Start free \u2192 https:\/\/mrc.fm\/hermeszap\n\nIn this video I'll show you how to set up Hermes Agent from scratch - the free open source AI assistant by Nous Research that runs on your own computer, remembers everything between conversations, and actually teaches itself new tricks as you use it. I'll walk you through the one line install, connecting it to Claude (or your favourite AI model), getting it onto your phone with Telegram, building self-improving skills, and finally connecting it to 9,000+ apps using Zapier MCP.\n\n00:00 - Chapter 1 - Hermes Agent Tutorial for Beginners\n00:25 - Chapter 2 - Hermes Agent Overview (vs OpenClaw, What's New)\n00:41 - Chapter 3 - Hermes Agent Installation (One Line Install)\n01:12 - Chapter 4 - Hermes Agent Setup AI Models (Claude, Nous Portal, OpenAI)\n02:05 - Chapter 5 - Hermes Agent Telegram Setup (BotFather)\n03:20 - Chapter 6 - Hermes Agent Identity and Persistent Memory\n04:12 - Chapter 7 - Hermes Agent Skills Library (700+ Pre-Built Skills)\n04:39 - Chapter 8 - Hermes Agent Custom Skills (Self Improving AI)\n05:23 - Chapter 9 - Hermes Agent Scheduled Tasks (Cron Jobs)\n05:41 - Chapter 10 - Hermes Agent Web Scraping (Watcher Skill)\n06:02 - Chapter 11 - Hermes Agent MCP Tools (Zapier, Gmail, Slack)\n07:27 - Chapter 12 - Hermes Agent Local AI Models (Ollama and Gemma 4)\n08:32 - Chapter 13 - Hermes Agent vs OpenClaw (Which to Choose)\n09:25 - Chapter 14 - Hermes Agent Final Thoughts and Conclusion","thumbs":{"m":{"w":320,"h":180,"hash":"Mo5Qa3DukiTaTpy1zsROmQ&ts=1781078627"},"x":{"w":800,"h":450,"hash":"L3zn3bQB5gZU9Boxm-WCNQ&ts=1781078627"},"y":{"w":1280,"h":720,"hash":"OZF88NvhLyhVjRClbIJY6g&ts=1781078627"},"i":{"bytes":"AXACg|CisyBANg4xzjrinLOhI\/djpjOKgH3RTo0GSSfpUNItassvCQqOVB5HbGDmnGB+PlQfQioRzFtLkZPNQbSHK8UrXKat0LTwSAZUIMDnkelFVdqkH58EfrRTsIRcnip49yqV2AgjvRRTY46DWcISrJhuOc00nfNnsaKKVht3FuJxKsa7QCnGR3oooqkjNn\/\/2Q=="}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/6QZBep7mW0c","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1801,"date":1779119426000,"forwards":"3","views":"210","text":"One of the main trends in time series forecasting over recent months has been the use of foundation models. Here is a great article from the skforecast library that explains how those models work and provides an example of implementation with the library.<br><br>Thanks to Javier Escobar Ortiz and Joaquin Amat Rodrigo for the great work on this open-source project!<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/skforecast.org\/latest\/user_guides\/foundation-forecasting-models.html\">https:\/\/skforecast.org\/latest\/user_guides\/foundation-forecasting-models.html<\/a><br><br>#ai #forecasting #datascience","text_length":469,"media":{"root":"\/00e\/CQcAAMoWZ2EAAAAA7MNun_1I8lw","photo":{"thumbs":{"m":{"w":320,"h":198,"hash":"aAtP2m_H79nXFbWPbatWxg&ts=1781078627"},"x":{"w":790,"h":490,"hash":"F2RXe1OD7Q3S362LbJgTHg&ts=1781078627"},"i":{"bytes":"AZACg|DL+X3pQEz1P5UDbjrzQAo+8fwFaEB8nTJx9KMJjqfyowD0bC+9KQmMAnPrQA0hccE\/lRS4UKctz2AopFWAbMc5HvSgIPVj6CmHoKB1pkj\/AJCOpA9KD5eOh+tR0p6Ci4DyEAIBJaimDrRSKP\/Z"}}}}},{"channel_id":1634145994,"post_id":1800,"date":1779036150000,"views":"47","text":"My weekly newsletter is out! \ud83d\uddde\ufe0f<br><br>This week&#039;s agenda:<br>\ud83d\udd39 Open Source of the Week - The Great Docs project<br>\ud83d\udd39 New learning resources - Stanford Frontier Systems course, Gemme 4 deep dive, running LLMs locally<br>\ud83d\udd39 Book of the week - Data Engineering with Generative and Agentic AI on AWS by Justin J. Leto, PE, MBA, PMP<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/p\/data-engineering-with-genai-book\">https:\/\/ramikrispin.substack.com\/p\/data-engineering-with-genai-book<\/a>","text_length":385,"media":{"root":"\/011\/CAcAAMoWZ2EAAAAAc_VhVqkVMKU","webpage":{"url":"https:\/\/ramikrispin.substack.com\/p\/data-engineering-with-genai-book","type":"photo","title":"Data Engineering with GenAI Book, The Great Docs Project | Issue 88","site_name":"Substack","display_url":"ramikrispin.substack.com\/p\/data-engineering-with-genai-book","description":"A weekly curated update on data science and engineering topics and resources.","thumbs":{"m":{"w":320,"h":160,"hash":"WYWp_rDBZEtJB0hstey3Lw&ts=1781078627"},"x":{"w":800,"h":400,"hash":"tgWW8ISeLkRah5eA9fnZuw&ts=1781078627"},"y":{"w":1280,"h":640,"hash":"sbNrKseeumIZ8U-v4R4WEQ&ts=1781078627"},"w":{"w":1600,"h":800,"hash":"qcZPe6_csQEEori0BeT2vA&ts=1781078627"},"i":{"bytes":"AUACg|BzgbCxfFQbkYnJOBUUjiV8jIGOlLI+AcEAY\/GklpqU5PoTAwHI6nHpUYiAjDHgZqGGTbIxdsgVI10rpsaMEfWk46aApNO7JY5lVhtYZoqukcO4HzCB6UUmkh3bI1QZxzSqgPJ5oorQhDiq4PFIY1z0oopDGhFx070UUUAf\/9k="}}}}},{"channel_id":1634145994,"post_id":1799,"date":1778899464000,"forwards":"1","views":"23","text":"Stanford Frontier Systems \ud83d\udc47<br><br>The following Stanford course hosts weekly sessions with global leaders solving the biggest bottlenecks in frontier technology progress.<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=tsQB0n0YV3k&amp;list=PLoROMvodv4rN447WKQ5oz_YdYbS74M5IA&amp;index=1\">https:\/\/www.youtube.com\/watch?v=tsQB0n0YV3k&amp;list=PLoROMvodv4rN447WKQ5oz_YdYbS74M5IA&amp;index=1<\/a>","text_length":259,"media":{"root":"\/00e\/BwcAAMoWZ2EAAAAA7MNun_1I8lw","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=tsQB0n0YV3k&list=PLoROMvodv4rN447WKQ5oz_YdYbS74M5IA&index=1","type":"video","title":"Stanford CS153 Frontier Systems | Jensen Huang from NVIDIA on the Compute Behind Intelligence","site_name":"YouTube","display_url":"youtube.com\/watch?v=tsQB0n0YV3k&list=PLoROMvodv4rN447WKQ5oz_YdYbS74M5IA&index=1","description":"For more information about Stanford's online Artificial Intelligence programs, visit: https:\/\/stanford.io\/ai\n\nFollow along with the course schedule and syllabus, visit: https:\/\/cs153.stanford.edu\/\n\nIn a CS153 Frontier Systems lecture, the class hosts Jensen Huang, CEO of NVIDIA, who argues computing is being reinvented for the first time in 64 years as software shifts from prerecorded execution to real-time generation, with NVIDIA's extreme co-design across chips, compilers, networks, and systems delivering a million-fold speedup over the past decade versus Moore's Law's 100x. \n\nHe walks through the architectural logic of Hopper (pre-training), Grace Blackwell NVLink72 (inference and decode), Vera Rubin (agents), and the upcoming Feynman generation built for swarms of agents and sub-agents, while pushing back on MFU as a misleading metric in favor of tokens-per-watt and real evals. \n\nHuang also defends open models like Nemotron, BioNemo, and Alpamayo as essential for safety, transparency, and democratizing AI across underserved languages and scientific domains, and forecasts compute energy demand growing roughly a thousandfold, making this the strongest market moment in history to invest in sustainable energy and grid upgrades. \n\nGuest Speaker:\nJensen Huang founded NVIDIA in 1993 and has served since its inception as president, chief executive officer, and a member of the board of directors.\n\nSince its founding, NVIDIA has pioneered accelerated computing. The company\u2019s invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined computer graphics, and ignited the era of modern AI. NVIDIA is now driving the platform shift of accelerated computing and generative AI, transforming the world's largest industries and profoundly impacting society.\n\nHuang has been elected to the National Academy of Engineering and in 2026 was appointed to the President\u2019s Council of Advisors on Science and Technology. He is a recipient of the Semiconductor Industry Association\u2019s highest honor, the Robert N. Noyce Award; the IEEE Founder\u2019s Medal; the Dr. Morris Chang Exemplary Leadership Award; and honorary doctorate degrees from Taiwan\u2019s National Chiao Tung University, National Taiwan University, Oregon State University, Huazhong University of Science and Technology, and Link\u00f6ping University. He has been named the world\u2019s best CEO by Fortune, the Economist, and Brand Finance, as well as one of TIME magazine\u2019s 100 most influential people.\n\nPrior to founding NVIDIA, Huang worked at LSI Logic and Advanced Micro Devices. He holds a BSEE degree from Oregon State University and an MSEE degree from Stanford University.\n\nFollow the playlist: https:\/\/youtube.com\/playlist?list=PLoROMvodv4rN447WKQ5oz_YdYbS74M5IA&si=DOJ5amlyRdyMJBhG","thumbs":{"m":{"w":320,"h":180,"hash":"gy-MIlPerySSa3SnHJb7Sg&ts=1781078627"},"x":{"w":800,"h":450,"hash":"ADlhSzJDsGpX_wank80uCQ&ts=1781078627"},"y":{"w":1280,"h":720,"hash":"j9faXvMbLSksgwwfW7IF6A&ts=1781078627"},"i":{"bytes":"AXACg|DUUCnbRjpSLSu4SNmPQCgRVkkCzhiuSo4qcOX24xzz1rIurp5GDBMjoMdasW98f3QlAz0zSGaMgyDRUck6EEc0UuZBZkau+Mlhx3x0qte3TKVjB37j0I4ooqhIz3vGdlIUAr+tNN00jAuBkdKKKCjQWRmiVmGCRRRRXM9y0f\/Z"}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/tsQB0n0YV3k","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1797,"date":1778424224000,"views":"118","text":"My weekly newsletter is out! \ud83d\uddde\ufe0f<br><br>This week&#039;s agenda:<br>\ud83d\udd39 Open Source of the Week - The exo project<br>\ud83d\udd39 New learning resources - Getting started with Hermes AI agent, building a Slack Python bot, introduction to Pi agent, Gemma 4 coder app<br>\ud83d\udd39 Book of the week - Building Large Language Models from Scratch: Design, Train, and Deploy LLMs with PyTorch by Dilyan Grigorov<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/p\/the-exo-project-getting-started-with\">https:\/\/ramikrispin.substack.com\/p\/the-exo-project-getting-started-with<\/a>","text_length":440,"media":{"root":"\/001\/BQcAAMoWZ2EAAAAAVk9ou28Qy0s","webpage":{"url":"https:\/\/ramikrispin.substack.com\/p\/the-exo-project-getting-started-with","type":"photo","title":"The exo Project, Getting Started with Hermes and Pi Agents, Building LLMs from Scratch | Issue 87","site_name":"Substack","display_url":"ramikrispin.substack.com\/p\/the-exo-project-getting-started-with","description":"A weekly curated update on data science and engineering topics and resources.","thumbs":{"m":{"w":320,"h":160,"hash":"Zj8CRcIgYTRVBPssw46ppg&ts=1781078627"},"x":{"w":800,"h":400,"hash":"ZD84IulYyqtTJg8M3IvD1g&ts=1781078627"},"y":{"w":1280,"h":640,"hash":"ovLhKP6kKOULqdOyzTLTeg&ts=1781078627"},"w":{"w":1600,"h":800,"hash":"eqrsD5tvCefUKn0nb9AhGw&ts=1781078627"},"i":{"bytes":"AUACg|CGGdWTpyOualMhIwvNU4iMfLTt7Zx61SaYnexcWZcfOOneo3lDMODt9M9ag3HuKbvPY1VkRcsiR8nBoqoWf1ooC5ATjpUi5ZQSTRRWZoiRWIFKeaKKYho+4xoooqkQ9z\/\/2Q=="}}}}},{"channel_id":1634145994,"post_id":1796,"date":1778156708000,"forwards":"1","views":"229","text":"Build Slack Bot with Python \ud83d\udc47<br><br>The following tutorial by NeuralNine provides a guide for building and setting up a simple Slack bot with Python.<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=Fnj7Qq8AHnw\">https:\/\/www.youtube.com\/watch?v=Fnj7Qq8AHnw<\/a>","text_length":190,"media":{"root":"\/00b\/BAcAAMoWZ2EAAAAAgz_tAKfx_ck","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=Fnj7Qq8AHnw","type":"video","title":"Coding Slack Bots in Python: Quick Start Guide","site_name":"YouTube","display_url":"youtube.com\/watch?v=Fnj7Qq8AHnw","description":"\ud83d\udcbb\ufe0f Need some help with a project or some consulting? Contact me here: https:\/\/www.neuralnine.com\/services\n\n\ud83d\udc0d The Python Bible Book: https:\/\/www.neuralnine.com\/books\/\n\ud83d\udcbb The Algorithm Bible Book: https:\/\/www.neuralnine.com\/books\/","thumbs":{"m":{"w":320,"h":180,"hash":"PkHcIEisne1hipEH66InOg&ts=1781078627"},"x":{"w":800,"h":450,"hash":"OPC8zbIXNyOAHPNvDtTj0Q&ts=1781078627"},"y":{"w":1280,"h":720,"hash":"uXbt6HAiyn0QsaNrqAKWNg&ts=1781078627"},"i":{"bytes":"AXACg|DJj2bx5n3am\/0bjk+\/WoYyA4LDIqVJRFcebGgYL2bp6UmrjTsOX7Lv+bdt9s0L9k6EMPfmoZn8yQvgAtyQOlWbGKORX3rk9uaeyDdlaby\/M\/dZ2470UkyhZWUdAcUUCGg4qzHchFQYYbOoB4PNFFADVmTyGQp856HtUsELm0aaJipXg8\/eFFFJjRTJJOScmiiimI\/\/2Q=="}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/Fnj7Qq8AHnw","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1795,"date":1778135598000,"views":"128","text":"Gemma 4 Coder Desktop App<br><br>The following video provides an introduction to a new open source project that provides a code generator based on Gemma 4.<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=KnrdxmsZEqA\">https:\/\/www.youtube.com\/watch?v=KnrdxmsZEqA<\/a>","text_length":194,"media":{"root":"\/00c\/AwcAAMoWZ2EAAAAAeq_pIerVx6E","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=KnrdxmsZEqA","type":"video","title":"Google's OFFICIAL Gemma 4 Coder Desktop App: This FREE & LOCAL App by Google is ACTUALLY CRAZY!","site_name":"YouTube","display_url":"youtube.com\/watch?v=KnrdxmsZEqA","description":"In this video, I'll be telling you about Gemma Chat, a new open-source local vibe coding app for Mac powered by Google's Gemma 4, and how it lets you build apps locally without API keys, cloud models, or a monthly subscription.\n\n--\nKey Takeaways:\n\n\ud83d\ude80 Gemma Chat is an open-source Electron app that runs Gemma 4 locally on Apple Silicon Macs using MLX.  \n\ud83d\udcbb You can build small apps, landing pages, games, dashboards, and more with a live preview and local file workspace.  \n\ud83d\udd12 Everything stays on your machine, so your prompts, code, and generated files remain private.  \n\ud83d\udee0\ufe0f The app supports Build Mode and Chat Mode, with tools like file editing, bash commands, web search, and URL fetching.  \n\ud83e\udde0 Gemma Chat uses an XML-style tool protocol, which is more reliable for smaller local models than JSON function calling.  \n\ud83d\udce6 The app supports multiple Gemma 4 model variants, including smaller options for lighter Macs and larger options for stronger performance.  \n\ud83c\udfa4 It even includes voice input through local speech-to-text with Whisper, making the workflow feel even more local-first.  \n\ud83d\udc4d Overall, Gemma Chat is a really cool proof of concept that shows how far local AI coding agents have come on Mac.","thumbs":{"m":{"w":320,"h":180,"hash":"X4u6pQh_V1sZqC1DZno-xQ&ts=1781078627"},"x":{"w":800,"h":450,"hash":"A9IAPQ-oVtaRHNLN4TsD_g&ts=1781078627"},"y":{"w":1280,"h":720,"hash":"VJ4nDhhR0BjqiSYMXkMLqQ&ts=1781078627"},"i":{"bytes":"AXACg|DNEMjqCsbEeoFL9nm7Rv8AlWhZqjW8bNIFIBGOPWpmijA4n6Dj5qLFcrMzy2SLLgrz3pEwzkDpWpLGkrc3A6k5471H9lTOftI4+lWtieRlOWNEIXOTjmilnYxylVbcB3xRRdEtMpoQHG4ZGeRVvzrL\/n3k\/wC\/lFFQUGyOT5olKL6E5pBHtYY5ooqugupGTk8UUUUgP\/\/Z"}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/KnrdxmsZEqA","type":"iframe","w":1280,"h":720}}}}]