https://huiahub.com/videos/this-is-how-you-build-agentic-rag-systems-that-work-suon2026-10-04T05:46:57.913Zhttps://i.ytimg.com/vi/sUoNoaatRvU/hqdefault.jpgTHIS is how you build agentic RAG systems that workAn 11-minute Weaviate explainer for developers whose RAG answers are poor: it splits an agentic RAG pipeline into five systems and where each one breaks.https://www.youtube-nocookie.com/embed/sUoNoaatRvU6822026-07-10T09:03:15.000Z https://huiahub.com/videos/but-what-is-cross-entropy-compression-is-intelligence-part-2-glyg2026-10-04T05:46:57.698Zhttps://i.ytimg.com/vi/GlYgs6v2YfU/hqdefault.jpgBut what is cross-entropy? | Compression is Intelligence Part 23Blue1Brown explains where the loss function for training LLMs comes from, building cross-entropy up from optimal codes. Good for anyone who trains or studies language models.https://www.youtube-nocookie.com/embed/GlYgs6v2YfU20312026-07-16T11:56:04.000Z https://huiahub.com/videos/prompt-caching-explained-stop-overpaying-for-ai-agents-skm42026-10-04T05:46:57.461Zhttps://i.ytimg.com/vi/SkM4k4SKvCM/hqdefault.jpgPrompt Caching Explained: Stop Overpaying for AI AgentsA 17-minute explainer on what prompt caching stores and the agent-code mistakes that break it, for developers paying for long AI agent sessions.https://www.youtube-nocookie.com/embed/SkM4k4SKvCM10362026-08-10T03:15:10.000Z https://huiahub.com/videos/agent-memory-explained-complete-architecture-ayfz2026-10-04T05:46:57.247Zhttps://i.ytimg.com/vi/aYfZN8t6AQs/hqdefault.jpgAgent Memory EXPLAINED - Complete ArchitectureA 28-minute walk through how Mem0 stores, ingests and retrieves agent memories, for developers who want long-term memory that goes past a single vector search.https://www.youtube-nocookie.com/embed/aYfZN8t6AQs17142026-08-17T03:15:35.000Z https://huiahub.com/videos/run-local-models-in-pi-llama-cpp-gguf-and-the-llama-command-5dsf2026-10-04T05:46:57.009Zhttps://i.ytimg.com/vi/5DsFr19wJFg/hqdefault.jpgRun Local Models in Pi: llama.cpp, GGUF, and the /llama CommandA six-minute Hugging Face quickstart for Pi users who want a private, offline coding agent running on a local GGUF model through llama.cpp.https://www.youtube-nocookie.com/embed/5DsFr19wJFg3712026-09-08T15:00:00.000Z https://huiahub.com/videos/flow-matching-for-beginners-arig23498-hxqz2026-10-04T05:46:56.774Zhttps://i.ytimg.com/vi/hXQZ6lyRCsI/hqdefault.jpgFlow matching for Beginners | @ariG23498A 28-minute beginner's explanation of flow matching on the Hugging Face channel that leans on visuals over equations, for people who want the intuition behind modern image generators.https://www.youtube-nocookie.com/embed/hXQZ6lyRCsI17022026-09-15T20:37:58.000Z https://huiahub.com/videos/transformers-js-v4-3-structured-output-in-the-browser-innv2026-10-04T05:46:56.564Zhttps://i.ytimg.com/vi/InnVG6pOPpM/hqdefault.jpgTransformers.js v4.3: Structured Output in the browserAn 11-minute Hugging Face walkthrough of Transformers.js 4.3 for JavaScript developers who need models in the browser to return valid JSON every time.https://www.youtube-nocookie.com/embed/InnVG6pOPpM6682026-09-16T07:49:24.000Z https://huiahub.com/videos/nemotron-3-diarization-who-said-that-pzuu2026-10-04T05:46:54.516Zhttps://i.ytimg.com/vi/PZuuOXNB3Vw/hqdefault.jpgNemotron 3 Diarization - Who Said That?Sam Witteveen explains speaker diarization and runs NVIDIA's Nemotron 3 Diarization on a full podcast, a 13-minute look for anyone building multi-speaker transcription.https://www.youtube-nocookie.com/embed/PZuuOXNB3Vw7902026-09-23T15:36:07.000Z https://huiahub.com/videos/gemini-3-8-flash-tts-with-voice-cloning-gdub2026-10-04T05:46:53.706Zhttps://i.ytimg.com/vi/GDUBXR-ql78/hqdefault.jpgGemini 3.8 Flash TTS with Voice CloningSam Witteveen walks through Gemini 3.8 Flash TTS, from voice design and cloning to pricing, with Colab code, for developers choosing a text-to-speech model.https://www.youtube-nocookie.com/embed/GDUBXR-ql7810312026-09-24T17:15:13.000Z https://huiahub.com/videos/in-context-retrieval-weaviate-podcast2026-10-24T13:05:23.605Zhttps://i.ytimg.com/vi/gCGEg7jJXh0/hqdefault.jpgIn-Context Retrieval with Siddharth Gollapudi - Weaviate Podcast #146!A 56-minute Weaviate Podcast episode for search and RAG engineers on using an LLM's attention over a million-token context as the retriever, and where that breaks.https://www.youtube-nocookie.com/embed/gCGEg7jJXh033742026-10-01T14:04:14.000Z https://huiahub.com/videos/image-decision-models-for-rpa-forms-scans-and-screenshots-l8yx2026-10-04T05:46:49.886Zhttps://i.ytimg.com/vi/L8YxigQoLaM/hqdefault.jpgImage Decision Models for RPA: Forms, Scans and ScreenshotsSam Witteveen tries two open decision models, ImaJev 4B and Jev Omni, on forms and screenshots for RPA, useful for automation builders who need a model to make yes/no or multiple-choice calls.https://www.youtube-nocookie.com/embed/L8YxigQoLaM9832026-10-02T14:30:27.000Z https://huiahub.com/videos/your-coding-agent-is-6-months-out-of-date-jakub-hojsan-exa-ckhp2026-10-04T05:46:49.673Zhttps://i.ytimg.com/vi/cKhpeEBnT1o/hqdefault.jpgYour Coding Agent Is 6 Months Out of Date — Jakub Hojsan, ExaFor developers whose coding or review agents misjudge new code: why a search tool alone falls short, and how Exa trims pages down to what the model needs.https://www.youtube-nocookie.com/embed/cKhpeEBnT1o7432026-10-02T15:30:31.000Z https://huiahub.com/videos/why-99-accurate-browser-agents-still-fail-derek-meegan-browserbase-5xi2026-10-04T05:46:48.791Zhttps://i.ytimg.com/vi/5xi_S1f9sDU/hqdefault.jpgWhy 99% Accurate Browser Agents Still Fail — Derek Meegan, BrowserbaseA 17-minute talk for anyone moving a browser agent from demo to production: the math of compounding step errors and an architecture that works around it.https://www.youtube-nocookie.com/embed/5xi_S1f9sDU10092026-10-02T21:30:15.000Z https://huiahub.com/videos/yolo-mode-safely-microvm-sandboxes-for-any-agent-rowan-christmas-docker-oe-l2026-10-04T05:46:48.576Zhttps://i.ytimg.com/vi/OE_lLNCNfQo/hqdefault.jpgYOLO Mode, Safely: MicroVM Sandboxes for Any Agent — Rowan Christmas, DockerA 12-minute Docker talk for developers who let coding agents run unattended: why an agent's built-in guardrails fall short and how microVM sandboxes contain an agent.https://www.youtube-nocookie.com/embed/OE_lLNCNfQo6952026-10-03T00:30:06.000Z https://huiahub.com/videos/your-llm-app-returned-200-ok-it-was-still-wrong-marina-petzel-datadog-rtoj2026-10-04T05:46:48.360Zhttps://i.ytimg.com/vi/rTojoVotlD8/hqdefault.jpgYour LLM App Returned 200 OK. It Was Still Wrong. — Marina Petzel, DatadogAn 18-minute talk for engineers who run LLM apps in production: which cost, safety and quality metrics to track beyond latency and error rates.https://www.youtube-nocookie.com/embed/rTojoVotlD810812026-10-03T01:30:33.000Z https://huiahub.com/videos/i-built-a-personal-ai-agent-on-a-raspberry-pi-jeremy-adams-neo4j-ouze2026-10-04T05:46:48.144Zhttps://i.ytimg.com/vi/oUZEt4EiPbk/hqdefault.jpgI Built a Personal AI Agent on a Raspberry Pi — Jeremy Adams, Neo4jJeremy Adams of Neo4j builds a wearable agent on a Raspberry Pi with NanoClaw, WhatsApp and graph memory, a 20-minute talk for builders of small personal agents.https://www.youtube-nocookie.com/embed/oUZEt4EiPbk12102026-10-03T16:30:34.000Z https://huiahub.com/videos/an-interaction-is-all-you-need-ivan-leo-google-deepmind-8avb2026-10-04T05:46:47.451Zhttps://i.ytimg.com/vi/8aVbXXvJUY4/hqdefault.jpgAn Interaction Is All You Need — Ivan Leo, Google DeepMindIvan Leo of Google DeepMind explains the Gemini Interactions API and Managed Agents in 17 minutes, useful for developers building agents on Gemini.https://www.youtube-nocookie.com/embed/8aVbXXvJUY410242026-10-03T19:30:16.000Z https://huiahub.com/videos/what-makes-open-models-fast-in-production-sujee-maniyam-nebius-tre12026-10-04T05:46:47.224Zhttps://i.ytimg.com/vi/TRe1u7dHYiA/hqdefault.jpgWhat Makes Open Models Fast in Production — Sujee Maniyam, NebiusA 20-minute talk for engineers serving open LLMs: a layer-by-layer list of inference optimizations, from NVFP4 to speculative decoding, after a Nebius product intro.https://www.youtube-nocookie.com/embed/TRe1u7dHYiA12322026-10-03T22:30:28.000Z https://huiahub.com/videos/stop-fine-tuning-to-fix-retrieval-problems-anant-srivastava-qfll2026-10-04T05:46:47.010Zhttps://i.ytimg.com/vi/qflLT3SoVbw/hqdefault.jpgStop Fine-Tuning to Fix Retrieval Problems — Anant SrivastavaA 20-minute talk for engineers about to fine-tune a model to fix wrong answers: a clear rule for what belongs in the prompt, in retrieval and in weights.https://www.youtube-nocookie.com/embed/qflLT3SoVbw12122026-10-04T00:00:35.000Z https://huiahub.com/videos/how-ai-models-scale-beyond-a-single-gpu2026-10-24T13:05:23.713Zhttps://i.ytimg.com/vi/qZBibWYcKH4/hqdefault.jpgHow AI Models Scale Beyond a Single GPU Across LLM WorkloadsA nine-minute IBM Technology explainer for engineers who need the basic vocabulary of distributed LLM inference: the four parallelism types and prefill versus decode.https://www.youtube-nocookie.com/embed/qZBibWYcKH45442026-10-06T11:00:06.000Z https://huiahub.com/videos/build-and-train-glm-5-3-flash-from-scratch2026-10-24T13:05:23.804Zhttps://i.ytimg.com/vi/-gfgQfw2g_E/hqdefault.jpgBuild & Train a GLM-5.3-Flash Model From Scratch with PythonA freeCodeCamp.org walkthrough for developers who want to read, train and RL-tune a small GLM-5.3-Flash-style model in Python, with all code on GitHub.https://www.youtube-nocookie.com/embed/-gfgQfw2g_E26662026-10-06T16:55:56.000Z https://huiahub.com/videos/n8n-full-course-scalable-ai-automations2026-10-24T13:05:23.936Zhttps://i.ytimg.com/vi/YY-egxTQirA/hqdefault.jpgn8n Full Course – Architect Scalable AI Automations from ScratchA 43-minute freeCodeCamp.org course that takes n8n from first workflow to agents, Slack approvals, error handling and cost monitoring, for builders new to the tool.https://www.youtube-nocookie.com/embed/YY-egxTQirA25852026-10-09T17:00:19.000Z https://huiahub.com/videos/three-questions-every-agent-engineer-should-answer2026-10-24T13:05:24.027Zhttps://i.ytimg.com/vi/oVKGKdIAgtg/hqdefault.jpgThree Questions Every Agent Engineer Should Be Able To AnswerA 14-minute LangChain talk on finding, reproducing and fixing agent failures using production traces, for engineers who run agents in production.https://www.youtube-nocookie.com/embed/oVKGKdIAgtg8472026-10-09T17:16:00.000Z https://huiahub.com/videos/train-to-deploy-loop-for-specialized-ai2026-10-23T13:05:23.154Zhttps://i.ytimg.com/vi/13YZ1EB9hjU/hqdefault.jpgStop Renting Intelligence: The Train-to-Deploy Loop for Specialized AI — Fireworks AIA 19-minute Fireworks AI talk on training open models on your own data and redeploying them in a continuous loop, for teams weighing closed-model costs.https://www.youtube-nocookie.com/embed/13YZ1EB9hjU11572026-10-11T22:30:33.000Z https://huiahub.com/videos/sandboxes-4-ways-to-isolate-coding-agents2026-10-23T13:05:23.251Zhttps://i.ytimg.com/vi/iH_wV8BbS24/hqdefault.jpgSandboxes Aren't Optional: 4 Ways to Isolate Coding Agents — Robert Brennan, OpenHandsA 14-minute talk from the OpenHands CEO comparing four ways to sandbox coding agents, for developers who run agents with broad permissions.https://www.youtube-nocookie.com/embed/iH_wV8BbS248622026-10-12T05:10:18.000Z https://huiahub.com/videos/how-inference-keeps-up-with-the-need-for-tokens2026-10-23T13:05:23.341Zhttps://i.ytimg.com/vi/_cRgl3maiT8/hqdefault.jpgHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet LabsA 22-minute AI Engineer talk for inference engineers that covers runtime tricks like paged KV cache and chunked prefill, then system-level disaggregation and kernel-writing agents.https://www.youtube-nocookie.com/embed/_cRgl3maiT813662026-10-12T05:36:56.000Z