Videos
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
Nemotron TwoTower employs a frozen reader and diffusion generator in parallel, achieving 2.4x speedup while retaining 98.7% of the original model's quality.
Compares Gemma 4B and Gemma 12B outputs on an e-commerce app, connects Claude Desktop via MCP server, and uses DeepEval, Ragas, and Hugging Face Evaluate with LLM-as-a-judge for assessment.
Explains Google's Open Knowledge Format (OKF), which formalizes Andrej Karpathy's LLM wiki pattern into plain markdown for agents to query folders without plugins, RAG pipelines, or vector databases.
Locally installs and tests Qwopus-3.6-35B-A3B-Coder, a thinking-off, token-efficient coding agent model.
Tests Ornith-1.0-35B performance in OpenClaw, Hermes, and Pi agent harnesses versus Qwen3.6 27B dense using its mixture-of-experts architecture.
Compares Ornith 35B and Qwen 3.6 35B-A3B using llama.cpp, llama-swap, and OpenCode on dual RTX 3090s while building a street-racing car OS, race-control interface, and live race simulator UI.
Tests Z.ai's GLM-5.2 via hosted web app, API, agent harness, and self-hosted setups using webpage building, Cursor integration, Remotion animations, and Inference.net traffic mirroring.
Compares Ornith 1 35B MoE against Qwen 3.6 35B A3B using Performance, Memory, Agency, OpenAI Human Eval, Sand Physics and Dungeon Crawler tests on a 16GB VRAM system.
Compares closed-source Sonnet 5 against open-model Ornith 35B to evaluate whether a local model can outperform its proprietary counterpart.
Tests Claude Sonnet 5 via browser OS, C++ skate game, subway scene, FPS, skydiving simulation, frontend design, city timeline, multimodal coding, low-poly F1, drum kit simulation, and terrain improvem
Tests Claude Sonnet 5 via real-world coding, SVG generation, agentic, and reasoning benchmarks against Opus 4.8 and GLM 5.2, covering CursorBench, token efficiency, pricing, and World of AI Benchmark
Demonstrates running local AI agents with Archestra and Ollama, watching tool calls live, and blocking misbehaving MCP servers in real time using open-source, self-hosted tools.
Demonstrates using natural language prompts in Reflect.run's recorder to generate tests via an AI Agent that auto-fills login credentials and form fields while reasoning through the UI.
Reviews and tests LongCat-2.0, a large-scale MoE language model with 1.6 trillion total parameters.
Locally installs and tests Ornith-1.0, a self-improving family of open-source models for agentic coding.
Demonstrates removing restrictions from Krea 2 Turbo via SGLang Quick Rebalancer, enabling reference images for consistency and targeted edits on the local AI image generation model.
Compares GLM-5.2 and Claude Opus 4.8 via skydiving simulation, Windows XP-style AI app, 3D model generation, and time travel scene tests evaluating reasoning, coding, creativity, and consistency.
Tests Qwen-AgentWorld-35B-A3B against Qwen3.6-35B-A3B using Performance, Memory, Agency, OpenAI Human Eval, Sand Physics, and Dungeon Crawler benchmarks on a system with 16GB VRAM and 32GB DDR4 RAM.
Demonstrates setting up DeepSeek's DSpark drafter on Qwen3-4B locally to reproduce accepted-length speedup using dspark_qwen3_4b_block7 on a single GPU.
Covers GPT-5.6 benchmarks, Minecraft demos, U.S. AI restrictions, Fable 5 embargo, Zhipu AI cybersecurity model, Anthropic enterprise growth, and Grok 4.5 testing rumors.
Tests Ornith-1.0-9B versus Gemma-4-12B in local AI coding tasks to evaluate whether Ornith's benchmark scores align with real-world performance.
Demonstrates wiring AnythingLLM, Pi, and n8n to a local llama.cpp engine via llama-swap for offline chat, document-based RAG, coding assistance, and automation.
Locally installed and tested Qwable-5-27B-Coder, a Qwen3.6-27B base lightly post-trained on 10 traces total.
Tests Ornith 1.0 local coding models via browser OS, subway scene/FPS generation, frontend design, C++, multimodal code, and agentic coding scenarios.
Installs and tests Krea 2, an image generation model, using ComfyUI.
Covers updates on Seedance 2.5, Happyhorse 1.1, GPT 5.6, Seed 2.1, Krea 2, Jalapeno chips, IBM sub nano chip, DanceOPD, Un-0, HIW 500, Lift4D, PerceptionDLM, Aleph ultrasound, Autodata and Sakana fugu
Runs MiniMax M3 locally using Inferencer App on Mac Studio M3 Ultra 512GB to evaluate performance against claims of higher scores than GLM, Kimi and Opus.
Demonstrates running DeepSeek models using DSpark, a method described as making inference significantly faster.
Tests Ornith-1.0-35B against Qwen3.6-27B using a Splunk Cyber CTF question and an agentic Pi extension build judged by Opus 4.8.
Locally installs and tests the Qwythos-9B-Claude-Mythos-5-1M-GGUF full-parameter reasoning model on Claude Mythos and Claude Fable datasets.
Ornith-1.0-397B is tested using Inferencer App v2.0.6 on M3 Ultra 512GB, reportedly topping GLM 5.2 and Claude Opus in benchmarks.
Locally installs and tests OpenJarvis with Ollama, an open-source framework for building personal AI agents running on local hardware.
Cohere Labs North Mini and Qwen 3.6 35B A3B are tested via 2D Driving Game, Fake Desktop, and Slime Maze tasks on a local system with 16GB VRAM and 32GB DDR4 RAM.
Demonstrates using Hermes Agent's /learn command to convert URLs, codebases, or conversations into reusable AI skills within seconds.
Demonstrates connecting the Hermes agent to a Discord server via a bot created through the Discord Developer Portal using the hermes gateway setup command.
Locally installs and tests Ornith-1.0, a self-improving family of open-source models for agentic coding.
Tests the speed impact of Multi-Token Prediction on GLM 5.2 using Inferencer App v2.0.6 on an M3 Ultra 512GB system.
Demonstrates fine-tuning Large Language Models using Unsloth, LoRA and Apple MLX, covering techniques from basics to methods used by DeepSeek R1.
Locally installed and tested Qwen-AgentWorld, identified as the first language world model covering seven agent interaction domains within a single model architecture.
Evaluates GLM 5.2 on dual Strix Halo via UD-IQ2_M quantization, measuring token generation/prompt processing speeds against DeepSeek V4 Flash and testing coding capability with SWE Bench verified mini
Breaks down Google's whitepaper "The New SDLC With Vibe Coding" on agentic engineering, highlighting the Agent equals Model plus Harness framework, context engineering, and token economics.
Demonstrates installing and comparing nine free skills and plugins for Claude Code, Codex, Cursor, OpenClaw, Hermes, VS Code, and GitHub Copilot, including GStack, Stop Slop, Graphify, Understand Anyt
A three-phase web coding challenge evaluates Qwen3.5 9B and Qwythos 9B on creating an iPhone-style UI, functional apps, and a launch site within a browser environment.
Thoroughly tests the Mistral OCR 4 model.
North Mini Code 1.0 is evaluated via Performance, Memory, Agency, OpenAI Human Eval, Sand Physics, and Dungeon Crawler tests on a system with 16GB VRAM and 32GB DDR4 RAM.
Locally installs and tests baidu/Unlimited-OCR using resources from Hugging Face.
Tests Krea-2-Turbo and Krea-2-Raw locally via SGLang for text-to-image quality and speed against Stable Diffusion and Flux-style models.
Locally installs and tests Microsoft FastContext-1.0-4B-SFT, a lightweight repository-exploration subagent designed for LLM coding agents.
Tests Sakana Fugu across browser workflows, subway scenes, FPS games, C++, multimodal coding, frontend design, and flight simulation.
Tests Sakana Fugu Ultra via real-world coding, reasoning, and agentic evaluations against Fable 5, GPT-5.5, Opus 4.8, and GLM 5.2 using LiveCodeBench, SWE-Bench, and GPQA.