The Untitled Linux Show covers the week’s hottest Linux news for desktop, gaming, and even enterprise. ULS is the weekly update you don’t want to miss, from the latest kernel development to the updates on your favorite apps! Each episode finishes with a killer command line tip from each host.
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.
Or, you can donate whatever you want:
https://paypal.me/thelinuxexp
Liberapay: https://liberapay.com/TheLinuxExperiment/
👕 GET TLE MERCH
Support the channel AND get cool new gear: https://the-linux-experiment.creator-spring.com/
Timestamps:
00:00 Intro
00:42 Sponsor: Proton Pass
01:55 Torvalds talks about AI reports
04:25 Torvalds merges guidelines for Linux security and AI reports
07:04 Wine now runs Adobe Lightroom CC on Linux
09:34 Vivaldi & Firefox revamp their whole user interface
13:20 Greg Koah Hartman says Rust could eliminate 80% of CVEs
15:00 Fedora removes Deepin Desktop packages
17:02 Changes for Bitwarden have the community worried
18:54 New Module Jail tool to mitigate Linux flaws
21:05 Microsoft uses Fedora as its base for Azure
22:40 HP sponsors LVFS
24:23 Fedora surveys contributors over "verified" status
26:51 Sponsor: Tuxedo Computers
27:40 Support the channel
Links:
Torvalds talks about AI reports
https://www.phoronix.com/news/Torvalds-AI-Tools-Can-Be-Great
Torvalds merges guidelines for Linux security and AI reports
Video by OpenProject | Open Source Project Management via YouTube
Hear from our CEO, Niels Lindenthal, as he talks about what he loves most about working at OpenProject. And a quick spoiler: we’re already building the next release.
Workspace agents in ChatGPT help teams turn repeatable workflows into shared agents that can pull in context, use tools, and move work forward on their own.
In this demo, you’ll see how admins and builders can set safeguards for workspace agents. Enterprise admins can centrally manage who can use, build, and publish agents, and define what agents are allowed to do. Builders can also configure when agents should ask for approval before taking specific actions, so agents work the way teams need them to across users and workflows.
Workspace agents are generally available to ChatGPT Business, Enterprise, and Edu.
How H2O.ai bridges visual no-code ML pipelines and code-first Python execution for diverse data science working styles.
AI teams contain visual thinkers, coders, and everyone in between. Driverless AI supports intuitive wizards and visual pipeline diagrams for feature engineering and model tuning. MLOps allows switching between UI-based row scoring and command-line batch execution. h2oGPTe agents generate sandbox-tested Python code that can be exported, modified, and used in automated testing—enabling teams to fluidly transition from a visual interface to a fully scriptable environment without losing any work.
Technical Capabilities & Resources
➤ Visual Pipeline Composition: Visualize feature engineering, model selection, and ensembling steps as interactive diagrams in Driverless AI.
🔗 https://docs.h2oai.com/driverless-ai/latest-stable/docs/userguide/scoring_pipeline_visualize.html
➤ No-Code to Code Conversion: Export UI workflows from Driverless AI into reproducible, executable Python scripts.
🔗 https://docs.h2o.ai/driverless-ai/latest-stable/docs/userguide/examples/autoviz_client_example/autoviz_client_example.html
➤ Custom Code Integration: Incorporate custom functions and recipes directly into Driverless AI workflows for granular control.
🔗 https://docs.h2o.ai/driverless-ai/latest-stable/docs/userguide/custom_recipes.html
Learn how to build and evaluate a production-style Retrieval-Augmented Generation (RAG) agent with MLflow. This is Part 1 of a two-part series on a complete workflow: register prompts and the agent, capture execution traces with ground-truth expectations, and run evaluations across multiple frameworks from a single MLflow interface.
What this video covers:
Use case: A “school assistant” agent that answers children’s questions about school policies (cell phones, attendance, and more) in a child-friendly tone.
👉 Stack: LangChain, FAISS, Amazon Bedrock, MLflow
Workflow highlights:
• Prompt registration in the MLflow Prompt Registry (versioning + aliases like "production" so prompts can change without redeploying code)
• Agent definition using MLflow’s standardized agent base class (logging, versioning, deployment patterns)
• Trace capture on evaluation questions, including retrieved context and final outputs
• Ground truth expectations from subject matter experts, logged with traces for evaluation reference
• Multi-framework evaluation in one place: Custom MLflow LLM judge, Ragas, Arize Phoenix, and a deterministic retriever scorer
Results: Aggregated and per-trace metrics with judge rationales, plus tracking over time (including moving averages) to monitor iteration.
Coming in Part 2: Aligning a custom judge with human SME feedback using natural language when generic LLM judges are less reliable in domain-specific settings.
🎤 Speaker: Joana Mesquita, MLflow Ambassador
🔗 Repo with the code: https://github.com/joanacmesquitaf/rag-agent-mlflow-evaluation
📖 Read the accompanying blog post for a deep-dive tutorial and code breakdowns: https://medium.com/@joana.c.mesquita.f/evaluating-generative-ai-with-mlflow-from-development-to-deployment-validation-85bc2bd5e7a9
Timestamps:
0:00 – Introduction & The Problem of Fragmented Evaluation
2:15 – Introduction to the MLflow GenAI Module
5:30 – Step 1: Setting up the MLflow Environment
8:45 – Step 2: Defining the Agent & Prediction Function
12:10 – Step 3: Structuring the Evaluation Dataset & Ground Truth
15:40 – Step 4: Configuring Scorers (Built-in & Custom Metrics)
18:55 – Step 5: Running mlflow.genai.evaluate() & UI Walkthrough
21:30 – Wrap-up & Preview of Part II
SpikerBot is a neuroscience robot that moves, reacts, and changes behavior based on the neural circuits you build in the app. No coding required. They recently launched a Kickstarter campaign and we’re excited to have them join us on the show. Build a Brain and Watch It Come to Life on OpenCV Live this week!
OpenCV is a 501(c)(3) registered non-profit in the United States. See how you can support open source CV & AI: http://opencv.org/support/
Watch along for your chance to win during our live trivia segment, and participate in the live Q&A session with questions from you in the audience.
Become a paid member of the channel to help us make more episodes https://www.youtube.com/channel/UCkrcW82Y2kbgU-U9RaYfgxw/join
Got a cool project of your own? Send it to us and you may be featured https://www.jotform.com/form/233105358823151
If you’re working on high-stakes applications like enterprise search, customer support, healthcare information, legal research, or financial services, it’s vital that an AI use provides accurate results. Hybrid RAG is a powerful approach for accuracy-critical AI use cases where factual answers matter most.
Learn from Sr. AI developer advocate David VonThenen as he builds a Hybrid RAG model using Graph + Vector RAG and Neo4j + OpenSearch.
Check the GitHub: https://bit.ly/4tTNJzv
Understand Graph RAG: https://bit.ly/4mR3ORR
Learn more about Hybrid RAG: https://bit.ly/4pz0D3b
Be sure to subscribe for all things AI!
Timestamps:
00:15: Typical vector embedding pipeline
00:35: Understanding semantic similarly
01:58: Graph-based retrieval and knowledge graphs
02:56: Hybrid RAG architecture model
03:44: Vector and hybrid-based retrieval demo with Neo4j and OpenSearch
06:34: The pros and cons of knowledge graphs and vector embeddings
Thai localization projects often face challenges with inconsistent translations, especially when .po translation memory contains mixed styles from outdated and newer sources. While LLMs can produce high-quality translations, they often lack consistency with project-specific tone and style.
In this talk, we introduce Lazy-L10N, an open-source localization tool designed to improve translation consistency using local LLMs and vector search.
Lazy-L10N builds a translation memory from .po files, uses pgvector for semantic retrieval of relevant examples, and leverages a local LLM to generate context-aware, style-consistent translations.
We demonstrate the system using real-world case studies from Okular and KDE Thai localization.
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
Supreet, a senior GenAI solutions architect at AWS Startups (Frontier AI team), presents a case study on using SageMaker multi-adapter endpoints to support a legal-tech SaaS with multiple customer datasets without deploying multiple model endpoints. After limited success with RAG and prompt engineering, the startup moved to fine-tuning using parameter-efficient QLoRA on an open-weights model (tested with Mistral 7B) to reduce cost and training time, training an initial ~100MB dataset in about two hours. A single real-time endpoint hosts the base model while multiple small adapters (about 50–200MB) are swapped in milliseconds via routing logic (implemented with AWS Lambda and keyword/LLM-based hybrid routing) to meet sub-5-second latency targets. Supreet emphasizes adapter-level evaluations using NLP metrics and LLM-as-a-judge with SME input, plus an AWS architecture involving S3, SageMaker training/evaluation, model registry, API Gateway, and monitoring.
00:00 Welcome and Intro
01:06 Session Setup and Slides
01:59 Legal Tech Case Study
03:10 Requirements and Constraints
04:42 Choosing QLoRA and Model
07:13 Multi-Adapter Endpoints Explained
09:39 Routing and Adapter Switching
11:46 Latency Results and Benefits
12:50 Evaluations and Architecture
14:14 Q&A Model Registry and Benchmarks
16:57 Deployment Layers and Monitoring
20:26 More Q&A Fine-Tuning vs RAG
24:53 Wrap-Up and Next Steps
Learn more about Zenith: https://zenith.finos.org
🌐 More about FINOS: https://www.finos.org/
📧 Join our newsletter: https://www.finos.org/sign-up
📥 Download the State of Open Source in Financial Services report: https://www.finos.org/state-of-open-source-in-financial-services
🎙️ Listen to our Open Source in Finance Podcast: https://www.youtube.com/@FINOS/podcasts
🗣️ Attend the next Open Source in Finance Forum: https://hubs.ly/Q03z9D9D0
LinkedIn: https://www.linkedin.com/company/finosfoundation
00:00 Welcome and Guest Intro
00:20 James Ashley XR Journey
02:53 Back to Smart Glasses
05:14 AI Accelerates XR Apps
08:05 Hunting the Killer App
10:24 SharePlay and Learning in XR
13:33 Design Philosophy in MR
16:26 Focus and VR Training
18:27 Star Wars vs Star Trek AI Lens
21:21 Will Developers Still Matter
23:38 AI Lowers the XR Barrier
26:40 Fragments and MR Storytelling
27:52 Blender MCP Breakthrough
32:26 Parting Advice and Closing
We use cookies on our website to give you the most relevant experience by remembering your preferences and repeat visits. By clicking “Accept All”, you consent to the use of ALL the cookies. However, you may visit "Cookie Settings" to provide a controlled consent.
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. These cookies ensure basic functionalities and security features of the website, anonymously.
Cookie
Duration
Description
cookielawinfo-checkbox-analytics
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".
cookielawinfo-checkbox-functional
11 months
The cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".
cookielawinfo-checkbox-necessary
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".
cookielawinfo-checkbox-others
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.
cookielawinfo-checkbox-performance
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".
viewed_cookie_policy
11 months
The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data.
Functional cookies help to perform certain functionalities like sharing the content of the website on social media platforms, collect feedbacks, and other third-party features.
Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.
Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics the number of visitors, bounce rate, traffic source, etc.
Advertisement cookies are used to provide visitors with relevant ads and marketing campaigns. These cookies track visitors across websites and collect information to provide customized ads.
