Videos
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
Demonstrates building a LangChain agent using create_agent with multiply and web search tools, comparing invoke versus stream modes, measuring token usage, applying ModelCallLimitMiddleware, and enabl
Compares Oh My Pi with Pi and OpenCode through initial setup, configuration tweaks, built-in tools, custom system prompts, compaction methods, sub-agents, and design philosophy analysis.
Tests MiniCPM5-2B in GGUF format, identifying it as the second model in the MiniCPM5 series hosted on Hugging Face under openbmb.
Tests MiniCPM5-2B locally.
Locally installs and tests ISTA-DASLab Qwen3.8-27B-GSQ-RCO-GGUF models using GSQ and RCO quantization methods.
Runs local LLMs like Qwen3.8, GLM-5.3 Flash, Gemma, Muse/Glimmer and coding agents Pi, Codex via LM Studio, oMLX, MTPLX, Ollama, llama.cpp on M5 Max.
Compares GPT-6 Astra and Claude Fable 5.1 using Hot Wheels physics simulation, Vision Pro FPS task, robot arm control, software efficiency, and Steve PC game build tests.
Tests Tiel Coder 35B A3B performance, memory, reasoning, OpenAI Human Eval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot on a 16GB local setup.
Tests Ponytail, a Claude Code plugin, on real coding tasks to evaluate its ability to reduce generated code volume by up to 94% while maintaining functionality and quality.
Checks whether GPT-6 Astra represents the arrival of AGI.
Reviews GPT 6 Astra capabilities across physics, ray tracing, Unreal video games, drawing, sprite animation, music composition, VR real estate, product commercials, math explainers, image identificati
Demonstrates Qwen3.8-Flash-Next on 4x RTX 3090s using DeepSeek Harness with MiniMax H3 for autonomous music video creation, comparing throughput against Qwen3.8-27B.
Benchmarks unsloth/Qwen3.8-Flash-Next-GGUF on RTX 3060 using llama.cpp and thecodacus/spec-wins coding lab with contradictory specs and decoys.
SkillSpector detects vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in AI agent skills.
Benchmark Qwen 3.8 27B Q4_K_M via llama.cpp on MacBook Pro M5 Max versus RTX 5090, analyzing memory usage, GGUF headers, KV cache behavior, and MTP drafting performance at 8K context.
Locally installs and tests OmegaClaw, a neural-symbolic agent framework based on the Hyperon AGI stack.
Demonstrates GPT-6 Astra use cases including one-shotting games, controlling computers via OpenAI's upgraded harness, building 3D environments in Blender and Unity, and operating real-world robots.
Covers GPT 6 Astra, Claude Fable 5.1, Gemini 3.8 Flash, Muse Spark 1.3, H3 World, SolarWM, TimesFM, Lucida, VideoDeltaNet, LLaDA image, Deepseek v4 flash vision, Qwen 3.8 0902, WeatherNext 3, Fly brai
Locally installs and tests Spark-X2.5-4B to evaluate its capabilities for making AI practical, efficient, and accessible.
Demonstrates converting Python functions to LangChain tools using the @tool decorator, binding them via bind_tools, executing calls through .invoke(), and returning results as ToolMessage for USD to I
Introduces Extropic Z1T, a family of transformer-like AI models designed for the Z1 chip rather than GPUs.
Tests Hy4 Preview against GLM 5.3 using Inferencer App Q4-INF quantization on Mac Studio M3 Ultra 512 GiB via thinking mode performance, UI testing, censorship checks, complex code modification, game
Runs GLM-5.3-Flash 1-bit via Unsloth and llama.cpp on GMKtec EVO-X2, testing Blockfall, Eruption, Blind Artist, and The Ledger with 9.2–9.6 tok/s performance.
Tests Gemini 3.8 Flash on coding, reasoning, agentic workflows, Three.js, and game dev, comparing it against GPT-5.6 Sol and Claude Opus 5 using DeepSWE and HLE-Verified benchmarks.
Tests GPT-6 Astra capabilities via browser workflows, C++ game development, FPS generation, frontend design, Chrono City timeline, Blender, Godot, and 3D printer simulation.
Demonstrates a Claude Code workflow using slash commands for pre-production and auto-editor, faster-whisper, and OBS for post-processing YouTube videos.
Locally installs and tests TimesFM 3.0 by Google Research for time-series forecasting using resources from Hugging Face.
Reviews GPT-6 Astra, Claude Fable and Mythos 5.1, Gemini 3.8 Flash, Muse Spark 1.3, FastH3, Atlas, Solaris, OpenClaw 2.0, Muse Voice Transcribe, MAI-Transcribe-2, Dyson Camerajet and NVIDIA acquiring
Tests Qwen3.8-27B GSQ-RCO IQ2_XS (~8.4GB, ~2.50 BPW) versus the 53.8GB BF16 original on an Apple M4 Mac Mini with 24GB RAM.
Locally installs Obscura, a Rust-based headless browser engine designed for web scraping and AI agent automation.
Demonstrates building a local translation pipeline using Fish Audio S2.1 Pro, covering voice creation, TTS workflow testing, and full translated clip generation.
Tests DeepSeek-V4-Flash-Vision-Exp-MLX on Mac Studio M3 Ultra using Inferencer v2.2.7 for image-to-game generation, thinking modes, AAA graphics, face recreation, OCR, procedural assets, logic, coding
Reviews GPT-6 Astra’s performance on FrontierMath, ARC-AGI-3, ExploitBench and DeepSWE, comparing results against Fable 5.1 and Opus 5 while demonstrating computer-use capabilities.
Locally installed and tested IFM's K2 Horizon models, specifically the 0.9B, 7B, and 32B variants.
Evaluates Claude Fable 5.1 via harness-bench using OpenCode, pi and DeepSeek Harness within Claude Code auto mode, reporting costs, token usage and Qwen 3.8-27B graded results.
First look at GPT-6-Astra based on personal usage experience.
Tests OpenAI's GPT-6 Astra in coding, computer use, browser control, 3D environments, Unity, Unreal Engine, and agentic workflows, comparing it against GPT-5.6 Sol and Fable 5.1 via benchmarks, speed,
Demonstrates using TalkWithMe to create AI personas with persistent memories across chat sessions, covering memory addition, editing, and defining noteworthy events.
Demonstrates authenticating AI agents like Claude Desktop, Claude Code, Codex, or Playwright/Puppeteer scripts via Browserless Auto Login and 1Password Service Accounts without exposing credentials.
Evaluates Qwen3.8-27B-GSQ-RCO-GGUF via Performance, Memory, Reasoning, OpenAI HumanEval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot tests.
Tests Claude Fable 5.1 via coding, gaming, 3D, and agentic evaluations, compares it against Claude Opus 5, and explains Mythos 5.1 for trusted organizations.
Tests Tencent's 700B+ MoE Hy4 using Workbuddy app to evaluate its maximum performance capabilities.
Tests Muse Spark 1.3 on long agentic tasks, benchmarks, vision, chemistry reasoning and multilingual capabilities.
Reviews Claude Fable 5.1 across interior design, ray tracing, Blender 3D modeling, financial presentations, music composition, deep research, identifying cancer, creativity, specs, performance and lea
Tests Claude Fable 5.1, Gemini 3.8 Flash, and OpenAI Astra using DeepSWE benchmarks and Artificial Analysis data.
Tests Meta Muse Spark 1.3 against Claude and GPT using browser workflows, C++, frontend design, FPS, 3D CAD, Blender, Godot, and the Chrono City timeline test.
Demonstrates an AI software factory where a PRD generates shipped code via Archon, illustrated by the fully autonomous creation of Dynachat.
Tests Gemini 3.8 Flash for delivering next-generation intelligence in agentic workflows and cybersecurity applications.
Tests Tencent Hy4 preview MIX-STQ1_0 GGUF locally against API versions via Slappis demo, Splunk CTF, and Estonia tasks, evaluating coding and agentic performance preservation.