[{"channel_id":1634145994,"post_id":1904,"date":1787713221000,"views":"10","text":"The new VScode version comes with new markdown editor functionality. One of the nice features is editing the markdown directly in preview mode \ud83d\udc47\ud83c\udffc<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/youtu.be\/7uyRMACA_pM?is=xQ1MI9QdWQdfv5H-\">https:\/\/youtu.be\/7uyRMACA_pM?is=xQ1MI9QdWQdfv5H-<\/a>","text_length":197,"media":{"root":"\/006\/cAcAAMoWZ2EAAAAAYzEd0sxmE0E","webpage":{"url":"https:\/\/youtu.be\/7uyRMACA_pM?is=xQ1MI9QdWQdfv5H-","type":"video","title":"New Markdown Editor in VS Code!","site_name":"YouTube","display_url":"youtube.com\/watch?v=7uyRMACA_pM","description":"This video walks through the latest VS Code markdown editing experience, from side-by-side preview and live updates to the new markdown editor that lets you modify content directly in preview while still seeing syntax update in real time. It also shows how to hand off markdown cleanup to an agent in an isolated worktree.\n\n\ud83c\udf99\ufe0f Featuring: Kayla Cinnamon (@cinnamon_msft)\n\n\ud83d\udcf2 Follow VS Code:\nX: https:\/\/x.com\/code\nBluesky: https:\/\/bsky.app\/profile\/vscode.dev\nLinkedIn: https:\/\/aka.ms\/VSCode\/LinkedIn\nGitHub: https:\/\/github.com\/microsoft\/vscode\nInstagram: https:\/\/www.instagram.com\/vscode.ig\/\n\n#vscode #developertools","thumbs":{"m":{"w":320,"h":180,"hash":"TJI35EQGIAjZGZ3SC73z9Q&ts=1787853641"},"x":{"w":800,"h":450,"hash":"MVPs-MUWWJaxSSLpWaSCHw&ts=1787853641"},"y":{"w":1280,"h":720,"hash":"iLGU-8lxiYDaXptqeoFbbQ&ts=1787853641"},"i":{"bytes":"AXACg|C4AuOWx+BpcKCQW5H+yahffuOHYD2fFM\/ef89G\/wC+61s+5hddi1tU9G\/Q1E5KrwMk9KZiU\/xv\/wB91Dcs6KmOSvJOaUtEVG0mWFY9D1HpRVQzMkgkC5VhRUqatqOUHfQ0HUqT8uOfXrTM0UVotiJBWdeSASuCTwR\/IUUVM9iqe42CYYaN+VIOB6GiiisWjoTP\/9k="}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/7uyRMACA_pM","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1903,"date":1787664719000,"views":"38","text":"I feature a data science book every week in my newsletter, and this week&#039;s pick focuses on Imbalanced Data: Myths, Mistakes and Modern Solutions by Soledad Galli, PhD.<br><br>The book challenges the common assumption that class imbalance must be fixed through resampling. It builds an evidence-driven approach to classification around model evaluation, decision thresholds, probability calibration, real-world error costs, and careful use of sampling techniques.<br><br>Topics include:<br>\u2705 Class imbalance foundations and the factors that affect model performance<br>\u2705 Classification metrics and how to match them to the decision problem<br>\u2705 Decision thresholds that reflect practical requirements<br>\u2705 Probability calibration and recalibration in Python<br>\u2705 Cost-sensitive learning and the costs of different errors<br>\u2705 Undersampling, data cleaning, and the tradeoffs of removing observations<br>\u2705 Oversampling, SMOTE, and the bias synthetic sampling can introduce<br>\u2705 Using AI to build and audit an imbalanced-learning pipeline<br><br>It is a practical resource for data scientists and machine learning engineers who want to make better decisions about metrics, thresholds, calibration, and resampling.<br><br>More details are available here: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.trainindata.com\/p\/imbalanced-data-myths-mistakes-solutions-book\">https:\/\/www.trainindata.com\/p\/imbalanced-data-myths-mistakes-solutions-book<\/a><br><br>\u267b\ufe0f Please share if you find it useful<br><br>\ud83d\udccc Subscribe to my newsletter: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/\">https:\/\/ramikrispin.substack.com\/<\/a>","text_length":1382,"media":{"root":"\/006\/bwcAAMoWZ2EAAAAAYzEd0sxmE0E","webpage":{"url":"https:\/\/trainindata.com\/p\/imbalanced-data-myths-mistakes-solutions-book","type":"article","title":"Imbalanced Data - Myths, Mistakes and Modern Solu","site_name":"Trainindata","display_url":"trainindata.com\/p\/imbalanced-data-myths-mistakes-solutions-book","description":"Master imbalanced data with practical, modern machine learning techniques. Learn why class weights and resampling don\u2019t improve performance, and how threshold tuning leads to better cost-sensitive decisions.","thumbs":{"m":{"w":320,"h":92,"hash":"WQviXNvhkEa0a1srv8HxMA&ts=1787853641"},"x":{"w":800,"h":230,"hash":"RE_TMvaF4RsGh8sRlT0BgQ&ts=1787853641"},"y":{"w":1280,"h":368,"hash":"ZsetF9KP7fhpIqkEeZY5gA&ts=1787853641"},"w":{"w":2560,"h":736,"hash":"2XunMV2GgsYl9dYDIFlzzg&ts=1787853641"},"i":{"bytes":"AMACg|DSfeG+Xrg89v8APWo4pfl39ctggc5PqKsMiuu1gCD2NRwooLHH3TtA9BUvoUhjXaqSCjZDEcVILgEkbGH1+mamoqiSPzh6GipKKnUeh\/\/Z"}}}}},{"channel_id":1634145994,"post_id":1902,"date":1787410391000,"views":"50","text":"My weekly newsletter is out \ud83d\udc47\ud83c\udffc<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/p\/skills-for-real-engineers-learning\">https:\/\/ramikrispin.substack.com\/p\/skills-for-real-engineers-learning<\/a>","text_length":103,"media":{"root":"\/001\/bgcAAMoWZ2EAAAAAVk9ou28Qy0s","webpage":{"url":"https:\/\/ramikrispin.substack.com\/p\/skills-for-real-engineers-learning","type":"photo","title":"Skills for Real Engineers, Learning AutoML | Issue 102","site_name":"Substack","display_url":"ramikrispin.substack.com\/p\/skills-for-real-engineers-learning","description":"A weekly curated update on data science and engineering topics and resources.","thumbs":{"m":{"w":320,"h":160,"hash":"BBY4o39WZv72tfvYb-3NCw&ts=1787853641"},"x":{"w":800,"h":400,"hash":"B_bia6RaWwLQ4aNRrSrxSg&ts=1787853641"},"y":{"w":1280,"h":640,"hash":"aeCY-OP6oQSEwUrhaQxv1Q&ts=1787853641"},"w":{"w":1600,"h":800,"hash":"b0vnLzvK66e06pIcyvsxXA&ts=1787853641"},"i":{"bytes":"AUACg|Cqk2RzTjOIWzuyR2qorhTnFGDJJk8UBdl7cHAmQYDdfY1MZwISuM8VDEcwGMHOKrmSk0NMjduTRQFyx9KKBMiBOamUfLnuRRRTBD0+U5BpCo3H60UUhjWPyH24ooooBn\/\/2Q=="}}}}},{"channel_id":1634145994,"post_id":1901,"date":1787319769000,"forwards":"1","views":"42","text":"The first step in the Docker \ud83d\udc33 workflow, after defining the environment requirements, is to define the Dockerfile.<br><br>In a nutshell, a Dockerfile is a text file containing the instructions Docker uses to build an image. It is one of the most important components of the Docker workflow. A well-designed Dockerfile can save development time, shorten image builds, and reduce infrastructure costs throughout the application lifecycle.<br><br>This is the second tutorial in the Docker 101 series focusing on the Dockerfile. We will learn how the Dockerfile works by using a practical example: dockerizing a FastAPI application. This includes:<br>\u2705 Defining requirements<br>\u2705 Setting up the Python version <br>\u2705 Defining a virtual environment and installing the required libraries<br>\u2705 Copying the FastAPI script file to the image and making it executable<br><br>The next tutorial in this sequence will focus on the next step in the workflow - the build. <br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/theaiops.substack.com\/p\/how-to-write-your-first-dockerfile\">https:\/\/theaiops.substack.com\/p\/how-to-write-your-first-dockerfile<\/a>","text_length":994,"media":{"root":"\/013\/bQcAAMoWZ2EAAAAAJC97GOG_yXw","webpage":{"url":"https:\/\/theaiops.substack.com\/p\/how-to-write-your-first-dockerfile","type":"photo","title":"How to Write Your First Dockerfile for FastAPI","site_name":"Substack","display_url":"theaiops.substack.com\/p\/how-to-write-your-first-dockerfile","description":"Learn how to write a Dockerfile for a FastAPI application using Python, a virtual environment and core Dockerfile instructions","thumbs":{"m":{"w":320,"h":160,"hash":"XvP52woq1Q_c5Yfkn53Ohw&ts=1787853641"},"x":{"w":800,"h":400,"hash":"-QdWszzLnfBlDEfRKgt8jA&ts=1787853641"},"y":{"w":1280,"h":640,"hash":"gdzlv9dKpsyv2eXjL6OJXg&ts=1787853641"},"w":{"w":1600,"h":800,"hash":"o7uIfyOGeTbtDOoy5Yxofg&ts=1787853641"},"i":{"bytes":"AUACg|CzktwefXtTTGB0zz2Bpd6bsYzQZAOcdqYDtigYyR3OTTUEbrkHPOOGpGmidcEjn3ojEaDjnJo0sIVZFQhC656daKAQCTk80Ug1Km45oLGiigoNxo3GiigADnmiiigR\/9k="}}}}},{"channel_id":1634145994,"post_id":1900,"date":1787068068000,"views":"47","text":"I feature an open source project every week in my newsletter, and this week&#039;s pick is Unsloth Studio.<br><br>Unsloth Studio is a browser-based interface for running and training models locally without building the workflow in code. It brings model discovery, chat, dataset preparation, fine-tuning, monitoring, export, and serving into one interface for Mac, Windows, and Linux.<br><br>Key features include:<br>\u2705 A local browser-based interface for running and training models<br>\u2705 Model discovery and chat with GGUF and Safetensors models<br>\u2705 Side-by-side model response comparison<br>\u2705 Tool calling, web search, and Python or Bash execution<br>\u2705 No-code fine-tuning configuration and training monitoring<br>\u2705 Data Recipes for turning files into training datasets<br>\u2705 GGUF, Safetensors, and LoRA model exports<br>\u2705 OpenAI-compatible API serving for applications and agents<br><br>More details are available here: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/github.com\/unslothai\/unsloth\">https:\/\/github.com\/unslothai\/unsloth<\/a><br><br>License: Apache 2.0<br><br>\ud83d\udccc Subscribe to my newsletter: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/\">https:\/\/ramikrispin.substack.com\/<\/a>","text_length":997,"media":{"root":"\/00d\/bAcAAMoWZ2EAAAAA6_Fg6skwlLw","photo":{"thumbs":{"m":{"w":320,"h":176,"hash":"hjXrHqQh2z4ORwC74ZENxw&ts=1787853641"},"x":{"w":800,"h":439,"hash":"BK7ovFnt7KcFJE1y_VaaLg&ts=1787853641"},"y":{"w":1280,"h":702,"hash":"ibaYulym3wC9IrZ2HSwkyw&ts=1787853641"},"i":{"bytes":"AWACg|DTZ1VyPn49FY1IrbhnBwfUEUHOeMUpPFADMrEoHzkfQtSrIH+6G\/FSP504dOaKACilooAQjnrRjtmiigAAxTXQMckkfQkUUUCYCMKc5b\/vo0UUUAf\/2Q=="}}}}},{"channel_id":1634145994,"post_id":1899,"date":1786827124000,"views":"45","text":"Issue 101 is out!<br><br>This week&#039;s agenda:<br>\ud83d\udd39\u00a0Open Source of the Week - Unsloth Studio<br>\ud83d\udd39\u00a0New learning resources - Hermes desktop workflows, ML system design, and Docker Sandboxes<br>\ud83d\udd39\u00a0Book of the week - Imbalanced Data: Myths, Mistakes and Modern Solutions by Soledad Galli<br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/p\/unsloth-studio-imbalanced-data-issue\">https:\/\/ramikrispin.substack.com\/p\/unsloth-studio-imbalanced-data-issue<\/a>","text_length":341,"media":{"root":"\/00e\/awcAAMoWZ2EAAAAA7MNun_1I8lw","webpage":{"url":"https:\/\/ramikrispin.substack.com\/p\/unsloth-studio-imbalanced-data-issue","type":"photo","title":"Unsloth Studio, Imbalanced Data | Issue 101","site_name":"Substack","display_url":"ramikrispin.substack.com\/p\/unsloth-studio-imbalanced-data-issue","description":"A weekly curated update on data science and engineering topics and resources.","thumbs":{"m":{"w":320,"h":160,"hash":"7je9Yzwgi5oS3qxcqXFu0g&ts=1787853641"},"x":{"w":800,"h":400,"hash":"Vz7aNbtAtaZvOKsBOscC4Q&ts=1787853641"},"y":{"w":1280,"h":640,"hash":"LEl5twMufGC087DHGn4-PA&ts=1787853641"},"w":{"w":1600,"h":800,"hash":"6xJgcR1g6qQzNKCxVyPbcw&ts=1787853641"},"i":{"bytes":"AUACg|DLWZ1XaDx9Kazlzljmm1JGgPzMcKO+KYXYchQw4HSiXBOR3okfceOAOgprGgQ2iiigAqdRmIDseaKKTGhNgpTEvpRRQMayqIyQOaKKKBM\/\/9k="}}}}},{"channel_id":1634145994,"post_id":1898,"date":1786636017000,"forwards":"4","views":"117","text":"Getting Started with Docker Sandboxes \ud83d\ude80<br><br>This tutorial from Docker walks through setting up an isolated development environment for AI-assisted coding. The five-minute tutorial covers:<br>\u2705 Installing the Sandbox CLI<br>\u2705 Authenticating with Docker<br>\u2705 Launching a sandbox<br>\u2705 Mounting a workspace<br>\u2705 Using the same sandbox with Claude and Codex<br><br>\ud83d\udcfd\ufe0f: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=9jfk1fdhXZo\">https:\/\/www.youtube.com\/watch?v=9jfk1fdhXZo<\/a>","text_length":385,"media":{"root":"\/003\/agcAAMoWZ2EAAAAAvwDoUbFJeyY","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=9jfk1fdhXZo","type":"video","title":"Getting Started with Docker Sandboxes in Under 4 Minutes!","site_name":"YouTube","display_url":"youtube.com\/watch?v=9jfk1fdhXZo","description":"Getting started with Docker Sandboxes is easier than you think! In this video, I show you how to get up and running in just a few commands - from installing the Sandbox CLI and authenticating your account to launching your first isolated development environment. You\u2019ll also see how to use the same Docker Sandbox with both Claude and Codex, making it easy to switch between AI coding agents while working from the same mounted workspace. Whether you\u2019re experimenting with AI-assisted development or simply want a safe environment to run code, Docker Sandboxes make it fast, simple, and secure to get started.\n\n\ud83d\udd25 Want More Docker Content?\nIf you found this demo exciting, hit that like button and subscribe for more! We\u2019ve got even more Docker demos coming your way in this ongoing series showcasing new tools, integrations, and powerful workflows to level up your projects. Stay tuned!\n\nWhere to find Docker:\nDocker: https:\/\/www.docker.com\/\nLinkedIn: https:\/\/www.linkedin.com\/company\/docker\nBluesky: https:\/\/bsky.app\/profile\/docker.com\nX: @docker\nInstagram: @dockerinc","thumbs":{"m":{"w":320,"h":180,"hash":"_0zaKr4aLIrLrU9wTfVhmQ&ts=1787853641"},"x":{"w":800,"h":450,"hash":"B1VjxDlqiDDFDIvw4QhdGA&ts=1787853641"},"y":{"w":1280,"h":720,"hash":"Muiom4OSb-VSyWhhULCUUw&ts=1787853641"},"i":{"bytes":"AXACg|B8ty8crIISwHcUgu3H\/LEjj3569OP85qR4mMjETMASOME4qLyX6C6lz9DWxFg+2SdoD0\/ripxKxtRJt2sex+tR+RISR9ofPPY04wskT5cv0OD7UnsFtdSJrhonXL71zz0oqKYjYgyMMR0HSislJmjirl0iRnbhNvGPWlAYH5ljx7UUVsY3EklWGMyEcD0rLnu5JcjOB\/dFFFRJlxI5JFb+D58fhRRRWZdz\/9k="}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/9jfk1fdhXZo","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1897,"date":1786635508000,"forwards":"4","views":"121","text":"ML System Design for Data Scientists \ud83d\ude80<br><br>This video from Andres Vourakis, a Senior Data Scientist at Nextory, walks through a production ML system design framework. The 17-minute video covers:<br>\u2705 Six-step design framework<br>\u2705 Four production requirements<br>\u2705 Trial-to-paid conversion example<br>\u2705 Layer-by-layer system design<br>\u2705 Interactive ML system map<br><br>\ud83d\udcfd\ufe0f: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=t3W3TJrNUnQ\">https:\/\/www.youtube.com\/watch?v=t3W3TJrNUnQ<\/a>","text_length":395,"media":{"root":"\/001\/aQcAAMoWZ2EAAAAAVk9ou28Qy0s","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=t3W3TJrNUnQ","type":"video","title":"ML System Design for Data Scientists (The Framework I Wish I'd Learned Sooner)","site_name":"YouTube","display_url":"youtube.com\/watch?v=t3W3TJrNUnQ","description":"The ML system design framework I use to build production ML systems that ship, from a senior data scientist with 8+ years of experience.\n\n\ud83d\udc49 Get my free course: MLOps for Data Scientists \u2192 https:\/\/futureproofds.com\/resources\/mlops-for-data-scientists?utm_source=youtube&utm_medium=video&utm_campaign=andres_vourakis_channel&utm_content=ml_system_design_framework\n\n\ud83d\udc49 Explore the interactive ML System Map I built \u2192 https:\/\/futureproofds.com\/tools\/ml-system-map?utm_source=youtube&utm_medium=video&utm_campaign=andres_vourakis_channel&utm_content=ml_system_design_framework\n\n52% of data scientist roles now ask for production skills, and ML system design is the foundation that unlocks that. In this video I walk you through the 6-step framework I use, grounded in Chip Huyen's book, and show it inside a real production ML system I built, layer by layer.\n\nWhat you'll get:\n\u2714\ufe0f The 6-step ML system design framework, explained with a design lens (not just a listicle)\n\u2714\ufe0f Chip Huyen's 4 requirements every ML system should meet\n\u2714\ufe0f How the framework maps to a real trial-to-paid conversion system I built\n\u2714\ufe0f The interactive tool where you can explore the system on your own, piece by piece\n\u2714\ufe0f A free MLOps course built specifically for data scientists\n\nTimestamps:\n00:00 Intro\n00:43 The full system\n01:27 The framework\n09:57 Designing the system\n16:26 Start deploying today\n17:08 Outro\n\n---\n\nAbout me:\nI'm Andres, Senior Data Scientist at Nextory with 8+ years in tech and applied AI\/ML. Over the past 2 years I've gone deep on integrating AI into data science work, from agentic workflows with LangGraph to shipping ML systems in production. I built Applio (an LLM-powered resume and job analysis system), a talk-to-your-data Slackbot for stakeholders, and presented at DataFest on agentic analytics. On this channel I share how senior data scientists can future-proof their careers as the field shifts.\n\n\ud83d\udcec My newsletter (15k+ data scientists): https:\/\/read.futureproofds.com\/subscribe\n\ud83d\udcbc LinkedIn: https:\/\/linkedin.com\/in\/andresvourakis\n\n---\n\n#MLSystemDesign #MLOps #DataScience #MachineLearning #AIforDataScientists","thumbs":{"m":{"w":320,"h":180,"hash":"23-0NqIw2rTG9r5RUjCqgA&ts=1787853641"},"x":{"w":800,"h":450,"hash":"MJkQtQ4eZKG1pvAcKIciYQ&ts=1787853641"},"y":{"w":1280,"h":720,"hash":"uy93FjWcLLkTojWlD0SZ4g&ts=1787853641"},"i":{"bytes":"AXACg|DUA5xxn0qOeYQRF2UntgU5s+cPlG3HzMaz9ReONGImZncghc5Awe1ACi7nCs8wjZO6r1FNGpQ\/882\/IVDJKxs2LOAGxgVSGOtJDehpG+SVwERh+FFZ8Z2vn05opiL0zMrHLEjpzVaSFW4JO4Hk0UVCGkCQooIfLD+VS2cABdi2QO2KKKdyrE5RfQ0UUUCP\/9k="}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/t3W3TJrNUnQ","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1896,"date":1786543164000,"views":"57","text":"The first tutorial in this series is out and focuses on the motivation for using Docker.<br><br><br><a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/theaiops.substack.com\/p\/why-ai-developers-should-learn-docker\">https:\/\/theaiops.substack.com\/p\/why-ai-developers-should-learn-docker<\/a>","text_length":160,"media":{"root":"\/00c\/aAcAAMoWZ2EAAAAAeq_pIerVx6E","webpage":{"url":"https:\/\/theaiops.substack.com\/p\/why-ai-developers-should-learn-docker","type":"photo","title":"Why AI Developers Should Learn Docker","site_name":"Substack","display_url":"theaiops.substack.com\/p\/why-ai-developers-should-learn-docker","description":"From \u201cworks on my machine\u201d to a reproducible workflow","thumbs":{"m":{"w":320,"h":160,"hash":"VqQ-XUVN-sFZM4N3oWK6RA&ts=1787853641"},"x":{"w":800,"h":400,"hash":"hHdGdupayyt9sIeETsQUvw&ts=1787853641"},"y":{"w":1280,"h":640,"hash":"iJBZ3M2MKDm9Fmck1-bzMA&ts=1787853641"},"w":{"w":1600,"h":800,"hash":"f7ywx7-gueRRstQKE908Rw&ts=1787853641"},"i":{"bytes":"AUACg|C7kEkUZXOOM1GsnzHJ4o3jPTv1oAe\/TpQOo71DMSyYQn86csgGNx+YU+gEuRRUIY5Jzx2opCuVN7Uu9vWiigYb29aaXO7rRRQA4O2DRRRQB\/\/Z"}}}}},{"channel_id":1634145994,"post_id":1895,"date":1786543161000,"views":"61","text":"Docker 101 \ud83d\udc33\ud83d\udc47\ud83c\udffc\n\nWant to learn Docker? I am starting a new series of tutorials focused on Docker for ML\/AI developers. The first tutorial is out.\n\nDocker isn't as hard as it sounds, but it has a steep learning curve, and the goal of this series is to smooth it out.\n\nWhat are the benefits of Docker? Reproducibility. \n\nReproducibility is critical in any form of software development, mainly when you ship your code to another machine (e.g., deploy or have teammates run it). \n\nThis Docker series is going to cover:\n\u2705 What is Docker and when should you use it\n\u2705 Containerizing a minimal Python AI application.\n\u2705 Writing Dockerfiles that remain fast and maintainable as a project changes.\n\u2705 Building reproducible environments with Docker Compose and Dev Containers.\n\u2705 Running local models with Docker Model Runner.\n\u2705 Designing container boundaries for agents, MCP tools, and Docker Sandboxes.\n\u2705 Testing, securing, and publishing multi-platform images through CI.","text_length":962,"media":{"root":"\/00c\/ZwcAAMoWZ2EAAAAAeq_pIerVx6E","photo":{"thumbs":{"m":{"w":231,"h":320,"hash":"xEvx_wltqT9CalhDuG6x0A&ts=1787853641"},"x":{"w":577,"h":800,"hash":"BcaiGKKHskDxqEN4c8I39w&ts=1787853641"},"y":{"w":923,"h":1280,"hash":"apt6TKnqtvH64h0EFX_-AA&ts=1787853641"},"i":{"bytes":"AoAB0|DKRijhh1FWopHePO7J7Ckj+zDiSFiw64apdsMbH9y2OOjVLsxq4sUQ8skpub1J6VXJbA3davwqsgYIpx\/vUy4tCxGwAH+LLdaQ2ymFYAnHJqSRyV3hGqZRKABvKgdOenFRnzkygk+X2Io0EtAguJRbMu3nPXHJqu0j55yKmSeXGVlJ7YNRzGaXBds46e1PQCxnIyzgd+\/H6U1\/mXaJUBPrn\/CiiqSQiJIwnHnR5\/Hj9KlbjHzA\/n\/hRRSsB\/\/Z"}}}}},{"channel_id":1634145994,"post_id":1894,"date":1786462641000,"forwards":"2","views":"59","text":"Meta Muse Glimmer \ud83d\ude80<br><br>Meta released a 30B open-weight agentic model under Apache 2.0 for local workflows on consumer hardware.<br><br>It supports tool use, long-horizon reasoning, failure recovery, text+image input, adjustable reasoning effort, and 100+ languages. A roughly 4-bit version fits under 20 GB.<br><br>More details: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/research.meta.ai\/blog\/introducing-muse-glimmer-open-agentic-model\">https:\/\/research.meta.ai\/blog\/introducing-muse-glimmer-open-agentic-model<\/a>","text_length":389,"media":{"root":"\/013\/ZgcAAMoWZ2EAAAAAJC97GOG_yXw","webpage":{"url":"https:\/\/research.meta.ai\/blog\/introducing-muse-glimmer-open-agentic-model","type":"photo","title":"Introducing Muse Glimmer: An Open Agentic Model That Runs on Your Device","site_name":"Meta AI Research","display_url":"research.meta.ai\/blog\/introducing-muse-glimmer-open-agentic-model","description":"Muse Glimmer is a 30-billion-parameter open agentic model from Meta Superintelligence Labs, optimized for always-on local workflows on consumer hardware.","author":"Meta Superintelligence Labs","thumbs":{"m":{"w":320,"h":168,"hash":"1CKU2OvJC1lbmChFJBVGtA&ts=1787853641"},"x":{"w":800,"h":420,"hash":"QvrbdGqSwL2wdeteiv35rA&ts=1787853641"},"y":{"w":1200,"h":630,"hash":"jFRBjNas2bsDNBAms451SQ&ts=1787853641"},"i":{"bytes":"AVACg|DWpDRSetMQlGaDSUwCiiigQ80lFFAxKSiigBKKKKAP\/9k="}}}}},{"channel_id":1634145994,"post_id":1893,"date":1786462274000,"forwards":"1","views":"67","text":"Hermes Desktop Workflows \ud83d\ude80<br><br>This video from Tonbi&#039;s AI Garage walks through recent Hermes desktop workflows. The 16-minute video covers:<br>\u2705 Remote machines over SSH<br>\u2705 Multi-session panes and tabs<br>\u2705 Drag-in session context<br>\u2705 Custom widgets with the Plugin SDK<br>\u2705 The Kanban plugin<br>\u2705 Agent delegation across researcher, writer, and verifier profiles<br><br>\ud83d\udcfd\ufe0f: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=bifDX18uyUk\">https:\/\/www.youtube.com\/watch?v=bifDX18uyUk<\/a>","text_length":396,"media":{"root":"\/013\/ZQcAAMoWZ2EAAAAAJC97GOG_yXw","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=bifDX18uyUk","type":"video","title":"Hermes Desktop Kanban, Custom Widgets, SSH Backend, Custom Layouts (X Short Videos)","site_name":"YouTube","display_url":"youtube.com\/watch?v=bifDX18uyUk","description":"The Hermes Agent desktop app has quietly gotten a lot smoother since launch \u2014 so here's a roundup of three ways I customize mine to fit my workflow.\n\n\ud83e\udde0 Run agents? Give them a knowledge base. Agent Wikis has free, curated LLM wikis on a ton of AI topics \u2014 plus a Pro tier ($9.99\/mo) for super-sized wikis with way more depth: https:\/\/agentwikis.com\/\n\nSign up for my FREE weekly newsletter, where I spill my unfiltered thoughts on the latest AI news, cool research, and projects I'm building: https:\/\/www.onchainaigarage.com\/\n\nPulling together a few shorts I posted on X into one place, I walk through the recent Hermes desktop upgrades I actually use every day: connecting to a remote machine over SSH right inside the app (no more VS Code Remote-SSH), customizing your workspace with multi-session panes, tabs, and drag-in session context, and building your own desktop widgets with the Plugin SDK. Then I dig into the first official plugin \u2014 the Kanban board \u2014 now brought from the web dashboard into the desktop app. I run a real workflow through it, letting the auto-decomposer delegate a knowledge-base build across researcher, writer, and verifier profiles.\n\nResources:\n\ud83d\udd17 Hermes Agent: https:\/\/github.com\/NousResearch\/hermes-agent\n\nTimestamps:\n0:00 - How far the Hermes desktop app has come\n2:04 - Connect to a remote machine over SSH in the app\n5:08 - Multi-session panes, tabs + drag-in context\n7:26 - Custom widgets with the Plugin SDK (memory + scores)\n10:05 - The first official plugin: the Kanban board\n11:37 - A live Kanban workflow: building a wiki\n15:50 - Wrap-up\n\n#HermesAgent #NousResearch #AIAgents #Kanban #DeveloperTools #PluginSDK #AIWorkflow #DesktopApp #Productivity","thumbs":{"m":{"w":320,"h":180,"hash":"M7MWEJquR1er27cd2-gUtA&ts=1787853641"},"x":{"w":800,"h":450,"hash":"tDD_CfuYrL7jjctiupT9iQ&ts=1787853641"},"y":{"w":1280,"h":720,"hash":"wu8cvSvEX1zI8t_GRrH5dg&ts=1787853641"},"i":{"bytes":"AXACg|CqiweUpJG7bnBXvjpTZli+URnJzkjb0pI1Dwj93uUdSBUYjIG\/GFbOKtWExCFPOAD+VJtHoPzoPFL27UxCllKEEDPbAFFITRQBbtbsJaeWUJwDgg4qlv8Am56elFFJRS2Bu4uV9Tn0xSh1Hc\/lRRTuAwtzxmiiilcZ\/9k="}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/bifDX18uyUk","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1892,"date":1786461809000,"forwards":"1","views":"23","text":"I feature a data science book every week in my newsletter, and last week&#039;s pick focuses on Transformers: The Definitive Guide - Applications Beyond NLP by Nicole K\u00f6nigstein.<br><br>The book starts with attention, embeddings, and transformer architecture, then shows how the same ideas extend across different data types and applications. Topics include: <br>\u2705 Time-series forecasting and anomaly detection <br>\u2705 Computer vision and image segmentation <br>\u2705 Image, video, audio, and music generation <br>\u2705 Reinforcement learning and world models <br>\u2705 Reasoning, coding, and AI agents <br>\u2705 Model optimization and production deployment<br><br>It is aimed at intermediate-to-advanced machine learning engineers, data scientists, and researchers who want to understand where transformers fit beyond language tasks.<br><br>More details are available here: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/learning.oreilly.com\/library\/view\/transformers-the-definitive\/9781098167004\/\">https:\/\/learning.oreilly.com\/library\/view\/transformers-the-definitive\/9781098167004\/<\/a><br><br>\ud83d\udccc Subscribe to my newsletter: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/ramikrispin.substack.com\/\">https:\/\/ramikrispin.substack.com\/<\/a>","text_length":966,"media":{"root":"\/00c\/ZAcAAMoWZ2EAAAAAeq_pIerVx6E","photo":{"thumbs":{"m":{"w":244,"h":320,"hash":"JfBoW01T_J-BUAA8TCPeLg&ts=1787853641"},"x":{"w":609,"h":800,"hash":"-l931m1s70bLOk4C0RnxRQ&ts=1787853641"},"y":{"w":975,"h":1280,"hash":"6OviScn2_TAMS216lmQwfw&ts=1787853641"},"i":{"bytes":"AoAB8|DUeVVchmIAGenFIbiMH736dKeykngnketJ5Z9T\/wB9GgBDcRcZbr7GnK6uCVOcVFLJFCVEkrKW6DJ5qcYxwcigBJN2w7WCn1NZN79sGB83JwCG4P4VqseQO3rSMpypznB7ikBV02KZd8lwDvOACTk4q8elIM96U9KYBxSEKeoBoooAQYUYAJpc5HQiiigD\/9k="}}}}},{"channel_id":1634145994,"post_id":1891,"date":1786369490000,"forwards":"2","views":"80","text":"Claude Code Full Course \ud83d\ude80<br><br>This course from freeCodeCamp, developed by EricWTech, walks through Claude Code setup and day-to-day workflows. The 82-minute course covers:<br>\u2705 VS Code setup<br>\u2705 Permission modes<br>\u2705 Plan mode and autonomous goals<br>\u2705 Claude skills<br>\u2705 Context and token usage<br>\u2705 Slash commands<br>\u2705 GitHub version control<br>\u2705 MCP tools and app deployment<br><br>\ud83d\udcfd\ufe0f: <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/www.youtube.com\/watch?v=7l6bXLAKyEI\">https:\/\/www.youtube.com\/watch?v=7l6bXLAKyEI<\/a>","text_length":402,"media":{"root":"\/00d\/YwcAAMoWZ2EAAAAA6_Fg6skwlLw","webpage":{"url":"https:\/\/www.youtube.com\/watch?v=7l6bXLAKyEI","type":"video","title":"Claude Code Full Course \u2013 Autonomous Goals, MCP, and VS Code Setup","site_name":"YouTube","display_url":"youtube.com\/watch?v=7l6bXLAKyEI","description":"Learn Claude Code with this comprehensive crash course taught by a former senior software engineer. You will learn everything from setting up your local environment in VS Code to executing autonomous tasks with goals and seamlessly deploying your applications. By mastering file structures, custom skills, and the Model Context Protocol, you will have the exact toolkit needed to automate your development and ship modern software.\n\n\u270f\ufe0f Course developed by @EricWTech \n\n\ud83d\udd17 Join Eric's Skool community: https:\/\/www.skool.com\/erictech\/about\n\n\u2764\ufe0f Support for this channel comes from our friends at Scrimba \u2013 the coding platform that's reinvented interactive learning: https:\/\/scrimba.com\/freecodecamp\n\n\u2b50\ufe0f Contents \u2b50\ufe0f\n- 0:00:00 Introduction & Course Overview\n- 0:02:33 Installing Claude Code on Your Local Machine\n- 0:03:24 Choosing an IDE & Installing VS Code\n- 0:06:51 Customizing VS Code Themes\n- 0:07:39 Starting and Managing a Claude Code Session\n- 0:11:51 Understanding Permission Modes (Plan, Accept Edits, Auto, Bypass)\n- 0:15:03 Using Plan Mode & Autonomous Goals (\/goal)\n- 0:24:24 Installing and Triggering Claude Skills\n- 0:34:48 Exploring File Structures and Directories\n- 0:44:36 Managing Your Context Window and Token Usage\n- 0:50:00 Essential Built-In Slash Commands\n- 0:53:18 Managing Version Control with GitHub\n- 1:02:44 Connecting Tools & Deploying Apps via MCP and CLI\n- 1:11:57 Frequently Asked Questions (FAQ)\n\n\ud83c\udf89 Thanks to our Champion and Sponsor supporters:\n\ud83d\udc7e @omerhattapoglu1158\n\ud83d\udc7e @goddardtan\n\ud83d\udc7e @akihayashi6629\n\ud83d\udc7e @kikilogsin\n\ud83d\udc7e @anthonycampbell2148\n\ud83d\udc7e @tobymiller7790\n\ud83d\udc7e @rajibdassharma497\n\ud83d\udc7e @CloudVirtualizationEnthusiast\n\ud83d\udc7e @adilsoncarlosvianacarlos\n\ud83d\udc7e @martinmacchia1564\n\ud83d\udc7e @ulisesmoralez4160\n\ud83d\udc7e @_Oscar_\n\ud83d\udc7e @jedi-or-sith2728\n\ud83d\udc7e @justinhual1290\n\n--\n\nLearn to code for free and get a developer job: https:\/\/www.freecodecamp.org\n\nRead hundreds of articles on programming: https:\/\/freecodecamp.org\/news","thumbs":{"m":{"w":320,"h":180,"hash":"pTbpoevk0xFRGafUsyD0xg&ts=1787853641"},"x":{"w":800,"h":450,"hash":"Dqmg0_8tUoCWfp_6PoR4JA&ts=1787853641"},"y":{"w":1280,"h":720,"hash":"Sot7t_Im8BT0kHq_f3AnaA&ts=1787853641"},"i":{"bytes":"AXACg|DOLAqBtAPrTnhxuxuOPb9aiq0Ry3Ax9O3NaydhRVxjQAH72f8AJ\/woeHarHJ49qewBDbV5+n+faoPLf0PTNZ3KsNooopiCn+ack7Rkn9aKK0kiExfPPHT\/ABo844xgYxjvRRUNIq7I6KKKAP\/Z"}},"embed":{"url":"https:\/\/www.youtube.com\/embed\/7l6bXLAKyEI","type":"iframe","w":1280,"h":720}}}},{"channel_id":1634145994,"post_id":1890,"date":1786291270000,"forwards":"1","views":"54","text":"I am starting a new series of tutorials focusing on Docker \ud83d\udc33 for ML\/AI Ops \ud83d\udc47\ud83c\udffc<br><br>I recently released a new LinkedIn Learning course focused on Docker for AI\/ML developers. While creating this course, I spent a lot of time preparing learning materials, and I decided to turn those materials into a sequence of tutorials.<br><br>Here is what this Docker series is going to cover:<br>\ud83d\udd39What is Docker and when should you use it<br>\ud83d\udd39 Containerizing a minimal Python AI application.<br>\ud83d\udd39 Writing Dockerfiles that remain fast and maintainable as a project changes.<br>\ud83d\udd39 Building reproducible environments with Docker Compose and Dev Containers.<br>\ud83d\udd39 Running local models with Docker Model Runner.<br>\ud83d\udd39 Designing container boundaries for agents, MCP tools, and Docker Sandboxes.<br>\ud83d\udd39 Testing, securing, and publishing multi-platform images through CI.<br><br>The tutorials will be available in my AIOps newsletter \ud83d\uddde\ufe0f <br>Please subscribe to receive the tutorials \ud83d\udc49\ud83c\udffc <a target=\"_blank\" rel=\"noreferrer nofollow\" href=\"https:\/\/theaiops.substack.com\/\">https:\/\/theaiops.substack.com\/<\/a>","text_length":963,"media":{"root":"\/003\/YgcAAMoWZ2EAAAAAvwDoUbFJeyY","webpage":{"url":"https:\/\/theaiops.substack.com","type":"photo","title":"The AIOps Newsletter | Rami Krispin | Substack","site_name":"Substack","display_url":"theaiops.substack.com","description":"Hands-on guides to the world of MLOps and AIOps. Click to read The AIOps Newsletter, by Rami Krispin, a Substack publication with hundreds of subscribers.","author":"Rami Krispin","thumbs":{"m":{"w":320,"h":167,"hash":"b23eI4EUFvO7sSZ4ktRpjQ&ts=1787853641"},"x":{"w":800,"h":417,"hash":"kWeXQrzfuaw8KKUWw8Gauw&ts=1787853641"},"y":{"w":920,"h":480,"hash":"1p7zZKDIG1T5oVxPUnP-BQ&ts=1787853641"},"i":{"bytes":"AVACg|CJrmONirHke1WrCZJHZkOdoPXisufPnv8AJnOO1XdHO2RyRtGKzUEkmbOcm2jU+0DHQH\/gQqVG3qD6+9RidO7\/AKVL171d0zKzW4tFGPeimIw+tWLEAzkEZBU0UVzx3OqezNDyI\/7g\/KpMYooroscrYUUUUAf\/2Q=="}}}}}]