AI

Video by H2O.ai via YouTube

A language model does not know your internal documents, and it does not know what happened after it was trained. Retrieval is how you close that gap.

Terms covered:
– Information Retrieval: finding relevant content from a large collection in response to a query
– RAG (Retrieval-Augmented Generation): retrieve relevant documents at the moment a question is asked, then generate a grounded answer from them
– Graph RAG: uses a knowledge graph to retrieve, so the system navigates relationships between entities instead of matching keywords
– Agentic RAG: treats retrieval as active reasoning. It rewrites queries, routes across sources, checks whether results are useful and retries when they are not.

Standard RAG for direct queries. Graph RAG when relationships matter. Agentic RAG when the retrieval itself needs to reason.

—
AI Fundamentals Glossary | H2O.ai University
Full playlist: https://www.youtube.com/playlist?list=PLAWKlIKS-66E
Free courses and certifications: https://h2o.ai/university

#RAG #GenerativeAI #AgenticAI #AIGlossary #H2Oai

Source

Video by PyTorch via YouTube

AI agents are moving beyond chat interfaces and onto physical devices. In her upcoming session on Hardware-Aware AI at PyTorch Conference North America 2026, Kavya Sri Chennoju from Arm will demonstrate how PyTorch, ExecuTorch, and Arm Device Connect work together to deploy AI agents safely onto edge hardware such as robot arms and wearables.

Join the open source AI community in San Jose, October 20-21: https://hubs.la/Q04v4SL60

Source

Video by NetApp Instaclustr via YouTube

Same chatbot, same question, two different answers, because two users have two different roles. In this tutorial, we add Auth0 login, three distinct roles, and a new Apache Cassandra backend to the MCP Gateway shoe store support chatbot, so each persona gets exactly the tools their job requires. No more, no less.

This is a follow-up to our first MCP Gateway video. If you haven’t seen it yet, start there for the base setup (HTTP + Kafka backends) before diving into this one.

Follow the blog: https://www.instaclustr.com/blog/mcp-gateway-tutorial-connect-an-ai-agent-to-apache-kafka-and-http-server-backends/

Ready to add role-based access control to your own AI agent? Start a free Instaclustr trial (no credit card required) and follow the blog + code linked above. https://console2.instaclustr.com/signup

Questions about your setup? Drop them below, happy to help.

Source

Video by CNCF [Cloud Native Computing Foundation] via YouTube

Join Alexa Griffith of Red Hat at KubeCon + CloudNativeCon North America, November 9-12 in Salt Lake City, Utah.

In “Cache Me If You Can: LLM Inference with llm-d (with fun drawings),” Alexa will explore how to make LLM inference on Kubernetes more efficient and cost-aware.

Learn how llm-d uses prefix cache-aware routing, disaggregated prefill and decode, and flow control to improve performance as inference workloads scale. Expect clear explanations, honest tradeoffs, and yes, fun drawings.

Explore the session:
https://bit.ly/4y5Gmqa

Register:
https://bit.ly/3BDI5XL

Source

Video by FINOS via YouTube

See how RBC accelerated financial workflows by 60% using AI agents.

Learn how the Royal Bank of Canada built an agentic system to process complex capital markets data, SEC filings, and news feeds. This breakdown covers the architecture behind their multi-agent orchestration setup and the open-source tools used to automate research.

Subscribe for more technical engineering breakdowns in finance.

Source

Video by SAP via YouTube

The same signals shaping your experience can also inform what happens behind the scenes.

At the Retail Innovation Lab, SAP’s Industry AI approach connects those signals across merchandising, inventory, fulfillment, supply chain, and customer experience, bringing autonomous commerce to life in a real store environment.

@shop_redone #NYFW #Retail

Source

Video by TWiT Tech Podcast Network via YouTube

The New York Times sues OpenAI and Microsoft. Internal communications reveal employees acknowledging data ‘theft’ and bypassing paywalls. Discovery in these cases exposes hilarious internal candor, making you wonder why anything is ever put in writing. #TechLaw #Copyright #OpenAI #Microsoft #NYTimes

Source

Video by Meta Developers via YouTube

The Meta VR Start Developer Competition is officially live! 🏆

Over the next eight weeks, we’re inviting VR developers to build a new VR app or significantly update an existing project and enter it for a chance to win your share of the $1M prize pool, including prizes ranging from $20,000 up to $100,000.

Get a head start on building for a new era of VR, and create experiences across entertainment, gaming, and productivity that are designed to enjoy with hands. If your project wins, it could get featured on our developer blog and across Meta social channels. 👀

Submissions close November 18. Terms & Conditions apply. See rules at the link in the comments. 🔗

#MetaVR #MetaVRGlasses #DeveloperCompetition

Source

Video by Linux Tex via YouTube

Get Theme Studio – Massive Introductory Discount
https://payhip.com/LinuxTex

Ubuntu is making a major change to how it delivers Linux kernel updates. Canonical is moving toward approximately WEEKLY Ubuntu kernel releases, replacing the existing 4/2 Kernel SRU model with overlapping two-week update cycles.

But why does a stability-focused Linux distribution suddenly need kernel updates every week?

In this video, we break down what Ubuntu’s new weekly kernel update strategy actually means, how Canonical plans to keep roughly two weeks of testing while releasing updates every seven days, and why this does NOT mean Ubuntu is becoming a rolling-release distribution or shipping a completely new Linux kernel version every week.

We also look at the huge explosion in Linux kernel CVEs. Kernel CVE counts jumped from only a few hundred per year to thousands after the Linux kernel became its own CVE Numbering Authority in 2024. Does that mean Linux suddenly became dramatically less secure? Not exactly.

We’ll also explore how AI-assisted security research is changing Linux kernel development, why AI is finding more potential bugs, and why human maintainers, backporting, verification and regression testing may increasingly become the real bottleneck.

And most importantly: what does all of this mean for your Ubuntu PC?

We cover:

• Ubuntu weekly kernel updates explained
• Canonical’s new Kernel SRU release schedule
• Why Linux kernel CVEs exploded
• Linux kernel security and CVE tracking
• AI-assisted Linux kernel bug discovery
• Ubuntu 24.04 LTS kernel updates
• Weekly kernel updates vs rolling releases
• Whether Ubuntu users will need to reboot every week
• Ubuntu Livepatch and kernel security fixes
• NVIDIA drivers and weekly kernel updates
• DKMS and out-of-tree kernel modules
• Kernel regressions, Wi-Fi and hardware problems
• Booting an older Ubuntu kernel if an update causes problems
• Whether faster kernel releases could affect Ubuntu stability
• What Canonical’s new strategy means for the future of Ubuntu Linux

Ubuntu says the testing process remains intact, with overlapping pipelines allowing one kernel candidate to be tested while the next one is already being prepared. The real question is whether Canonical can maintain the reliability Ubuntu users expect while increasing kernel release frequency this dramatically.

If you use Ubuntu, Ubuntu 24.04 LTS, Linux Mint, GNOME, NVIDIA on Linux, or simply follow Linux kernel security and desktop Linux development, this is a major change worth understanding.

#Ubuntu #Linux #LinuxKernel #UbuntuLinux #Canonical #LinuxSecurity #OpenSource

Timestamps:
0:00 Introduction
0:45 So What Actually Changed?
2:55 Why Ubuntu Suddenly Needs This
6:28 Theme Studio
7:36 What This Means for Your Ubuntu Machine

Source

Video by The Linux Cast [Matthew Weber] via YouTube

The boys are back! Tonight we talk about AI use in FOSS projects

==== Special Thanks to Our Patrons! ====
https://thelinuxcast.org/patrons/

===== Follow us 🐧🐧 ======
Discord – https://thelinuxcast.org/discord
Odysee – https://odysee.com/$/invite/@thelinuxcast:4
Mastodon- https://fosstodon.org/@thelinuxcast

Subscribe at http://thelinuxcast.org
Contact us email@thelinuxcast.org
https://facebook.com/thelinuxcast

# Drew
– Odysee – https://odysee.com/@justaguylinux:c
– YouTube – https://youtube.com/JustAGuyLinux
– Mastodon – https://fosstodon.org/@justaguylinux
– Website – https://justaguylinux.com

# Nate
– YouTube – https://www.youtube.com/@NatePicksTechWorld
– Mastodon – https://fosstodon.org/@NatePick
– Discord – https://discord.gg/wHCjfSk

#Support Us
MERCH – https://shop.thelinuxcast.org
Patreon – https://patreon.com/thelinuxcast
PayPal – https://paypal.me/thelinuxcast
Kofi – https://ko-fi.com/thelinuxcast
Sponsored by Proton – https://go.getproton.me/SH1gC

#Credits
Logo courtesy of pedropaulo.net
Intro courtesy of https://www.fragcgi.com/?i=1

[show notes]
https://git.thelinuxcast.org/notes/s10/1026.md

Source