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.
Video by OpenAI via YouTube
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.
Video by H2O.ai via YouTube
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
Video by MLflow via YouTube
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
Video by OpenCV via YouTube
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
Video by NetApp Instaclustr via YouTube
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
Video by FOSSASIA via YouTube
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
Session slides: https://eventyay.com/ev/88882f3e/talk/R5MK5NQE2NCX/
#FOSSASIA #FOSSASIASummit #opensourcegames #FOSS
Video by FINOS via YouTube
Multi-Adapter Endpoints on AWS: Cost-Optimized Fine-Tuning with QLoRA for Multi-Customer Legal GenAI
https://github.com/aws-samples/sagemaker-genai-hosting-examples/tree/main/06-examples/01-train-deploy-LoRA
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
Video by Open Data Science and AI Conference via YouTube
Powered by 100 millionm miles on public roads and billions more in simulation, the Waymo Driver is the most advanced application of AI in the physical world today. Waymo collects massive amounts of data from real roads and billions of miles driven in computer simulations. Manasi Joshi, director of Systems Intelligence and Machine Learning, will explain how Waymo’s engineers use these huge datasets to advance how cars "see" the world, predict what other drivers will do, and plan their routes. You’ll hear about how Waymo uses ML to train and test these self-driving systems and how its open dataset is motivating further public research in autonomy. This work helps make Waymo’s autonomous vehicles safer and more reliable every day in an era of rapid expansion and competition of autonomous ride-hailing services.
————————————————————————————————————-
Visit our website and choose the nearest ODSC event to attend and experience all our training and workshops: https://odsc.ai
To watch more videos like this, visit https://aiplus.training
Sign up for the newsletter to stay up to date with the latest trends in data science: https://opendatascience.com/newsletter/
Follow us online!
• Facebook: https://www.facebook.com/OPENDATASCI
• Instagram: https://www.instagram.com/odsc/
• Blog: https://opendatascience.com/
• LinkedIn: https://www.linkedin.com/company/open-data-science/
• X (twitter): https://x.com/_odsc
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 all seem to be moving away from Ubuntu, but there are still quite a few reasons to keep using it.
https://linuxafterdark.net/linux-after-dark-episode-122/
