HM Godoy

Video by TWiT Tech Podcast Network via YouTube

Windows Weekly is about more than Windows. Veteran Microsoft insiders Paul Thurrott and Richard Campbell join Leo for a deep dive into the most valuable company in the world. From consumer to enterprise, AI to Xbox, Windows Weekly is the only Microsoft podcast you’ll ever need.

You can find more about TWiT.tv and subscribe to our full shows at https://podcasts.twit.tv
Join our community at Club TWiT: https://twit.tv/clubtwit

About us:
TWiT.tv is a technology podcasting network located in the San Francisco Bay Area with the #1 ranked technology podcast This Week in Tech hosted by Leo Laporte. Every week we produce over 30 hours of content on a variety of programs including Tech News Weekly, MacBreak Weekly, Windows Weekly, Security Now, Intelligent Machines, and more.

Source

Video by MLflow via YouTube

In the ninth tutorial of the Mastering MLflow for GenAI series, Jules Damji (Databricks) builds a complete RAG application, instrumented with full MLflow observability—from query and document embedding and semantic search retrieval through LLM generation, performance analysis, and RAGAS quality evaluation.

What You’ll Learn:
🔹 End-to-end RAG pipeline instrumented as typed spans (PARSER, EMBEDDING, RETRIEVER, LLM, CHAIN): validate → embed → retrieve → assemble → generate → validate.
🔹 @mlflow.trace instrumentation plus mlflow.openai.autolog() for automatic LLM tracing.
🔹 Performance analysis across test queries: latency, token usage, cache hits, and estimated cost.
🔹 RAGAS Faithfulness and Context Relevance via mlflow.genai.evaluate() on traces with RETRIEVER spans.
🔹 Production notes: in-memory store and cosine similarity for teaching; swap in vector DBs and hybrid BM25 and semantic searches for real deployments.
🔹 MLflow UI & multi-level tracking and tracing: experiment config, per-query runs, per-step latency/tokens/cost, full pipeline timeline, span attributes, and latency bottlenecks.

Next in the Series: Notebook 1.10 covers the Multi-Agent Supervisor pattern with LangGraph.

Resources:
🔗 Notebook 1.9: https://github.com/dmatrix/mlflow-genai-tutorials/blob/main/09_complete_rag_application.ipynb
🎥 Full Series Playlist: https://youtube.com/playlist?list=PLaoPu6xpLk9EI99TuOjSgy-UuDWowJ_mR

Source

Video by Hugging Face via YouTube

Text generation looks like one function call. Underneath, it’s a loop: infer, pick a token, append it, repeat. Watch how Transformers.js runs an LLM step by step.. and understand what’s actually happening every time you chat with one.

Source

Video by NetApp Instaclustr via YouTube

Your AI agent is smart—but struggles with your data because of complex integrations. Enter Model Context Protocol (MCP), an open standard that connects AI to tools and data without custom work. Instaclustr for MCP Gateway makes it production-ready with secure, scalable, and governed access.

See MCP Gateway in action in this demo and read more in the announcement blog: https://www.instaclustr.com/blog/netapp-instaclustr-for-mcp-gateway-is-here-smarter-ai-data-access-starts-now/

Try the MCP Gateway free (console, Terraform, or API): https://console2.instaclustr.com/signup

Full shoe store chatbot code: https://github.com/instaclustr/code-samples/tree/main/MCP-Gateway/shoe-store-support-chatbot

Source

Video by FOSSASIA via YouTube

Can you run ChatGPT securely on your own network? This panel explores how to build a private AI assistant using local LLMs without sending sensitive data to the cloud.

Learn how to deploy and compare popular local AI runtimes, including Ollama, Docker Model Runner, and Foundry Local, then integrate them into intelligent applications with .NET Aspire and Microsoft.Extensions.AI. The discussion also covers extending the same architecture to cloud-hosted LLMs, balancing privacy, performance, flexibility, and developer experience.

Whether you’re building enterprise AI, self-hosting open source models, or exploring ChatGPT alternatives, this session provides practical guidance for creating secure, production-ready AI applications.

FOSSASIA Summit 2026 held in Bangkok, is Asia’s leading Open Source tech conference featuring sessions on #AI, #Cloud, #DevOps, #Open Hardware, #Security, #Web #Mobile Technologies, #Web3, and #Databases. Learn more: http://summit.fossasia.org

Session slide: https://eventyay.com/ev/88882f3e/talk/QBVLQE7WDBHP/

#FOSSASIA #FOSSASIASummit #opensource #FOSS

Source

Video by Trino via YouTube

– 00:00 Intro, Trino query UI, and JavaScript client publishing
– 00:48 Autoscaling, KEDA, and Resource-aware admission control
– 08:24 Trino Maven plugin rewrite
– 09:12 TPC-DS Test Suite spec v4 updates
– 10:26 Trino Statement Utils compatibility in Trino Gateway
– 11:21 New Trino online sandbox: trysql.io

More details available in the meeting minutes at
https://github.com/trinodb/trino/wiki/Contributor-meetings

Call organized and hosted by Manfred Moser. Sponsor him at
https://github.com/sponsors/mosabua to support this and other open source initiatives.

Source

Video by The Late Night Linux Family via YouTube

Support us on Patreon and get an ad-free RSS feed with some early episodes. https://www.patreon.com/LateNightLinux

We finally have pricing for the Steam Machine, but they are very hard to actually buy, and very expensive. SteamOS is now supported on your own hardware now though, and Joe gives it a go. Plus Ubuntu makes moves to tighten up the flavours situation and announces speech to text on the desktop, and a quick KDE Korner.

https://latenightlinux.com/late-night-linux-episode-392/

Source