Videos
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
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.
Muse Glimmer is rematched against Qwen 3.8 27B using TalkWithMe, with Qwen’s reasoning level increased to high for comparison.
Tests Inworld Realtime TTS-2 and TTS-2 Flash for voice quality, cloning, steering, multilingual support, and API integration against ElevenLabs.
Tests Qwen3.8-Max-0902, described as an upgraded snapshot of qwen3.8-max.
Evaluates OLMo using traces, tokens versus wall clock comparisons, souping methods, and performance metrics on a private H100 cluster.
Evaluates Claude Fable 5.1 via BridgeBench, Claude Code in BridgeMind One, and comparisons against Fable 5, Opus 5, GPT 5.6 SOL, Grok 4.6, and Kimi K3.
Evaluates Claude Fable 5.1 via browser OS tests, C++ skate and rally games, 3D CAD models, frontend design, watch websites, and an UltraCode Subway FPS test.
Introduces and tests Fable 5.1 and Mythos 5.1.
Demonstrates building short term memory with MessageHistory, MemorySaver, trim_messages, and SummarizationMiddleware, plus long term memory via InMemoryStore and SQLite in LangChain.
Eleven universal tips for improving coding agent reliability cover instruction hygiene, context management, avoiding escalation, and systematic validation based on cited studies.
Tests FreeToken against llama-server baseline using OpenCode on 12GB VRAM to evaluate performance constraints.
Tests MTPLX v2.10.0 optimizations for local Qwen3.8-Flash-Next coding agents via .NET migration and SVG image generation comparisons against oMLX.
Compares Grok Bot and Hermes Agent setups, capabilities, and reliability for automated workflows and local action execution.
Locally installs and tests JetSpec's speculative decoding to demonstrate real speedup numbers for large language model inference.
Tests Tencent HY4 Preview on coding, 3D game dev, and agentic tasks, comparing it against Qwen 3.8, GLM 5.3, DeepSeek V4 Flash Vision, Kimi K3, Claude Opus 5, and GPT-5.6 using WOAI Bench.
Benchmark compares Qwen 3.5 9B, Ornith 1.5 9B, Defiant Fable, Heretic Qwen, and Hauhau Qwen on 12GB GPUs like 3060, 4070, or 1080 Ti.
Locally installed and tested open-weight text-to-speech model Breeze TTS 2, designed for real-time interaction.
Benchmarked Qwen3.8-Flash-Next in llama.cpp across 0–96GB VRAM using AMD Ryzen 9 9950X and NVIDIA RTX PRO 6000 Blackwell, measuring decode speeds, prefill gains, and configuration impacts.
Tests Tencent HY4 preview on browser workflows, C++ game creation, FPS development, frontend design, Blender scene generation, and a wrestling game.
Compares a $60,000 512GB Mac Studio cluster running Kimi K3 against a $10/month cloud coding agent to evaluate performance differences.
Demonstrates setting up DeepSeek Harness with local Qwen 3.8 27B via Ollama to autonomously build and deploy a portfolio site to Vercel using GPU-generated tokens.
Compares the Pi coding harness against OpenCode through testing network proxies, system prompts, roles, subagents, compaction, and integration with Agent Voice.
Demonstrates SureThing.io, a browser-based platform enabling zero-infrastructure AI agents that handle messaging, research, and deliverables via simple texting.
Evaluates Zhipu GLM-5.3 using Inferencer App on Mac Studio M3 Ultra 512 GiB with GLM-5.3-MLX-Q4-INF, testing thinking modes, coding stress tests and logic against cloud performance.