| Context Language Models Explained!Short | Oct 5, 2026 | 1:00 | 575 |
| Context Language Models: Your Agent Doesn't Need Compaction | Oct 5, 2026 | 13:54 | 12.4K |
| What Are Claude Code Mods?Short | Oct 3, 2026 | 1:11 | 21.3K |
| Claude Mods - The Biggest Claude Code Upgrade! | Oct 3, 2026 | 10:37 | 56K |
| Gemini 4 Argon Explained | Oct 1, 2026 | 7:42 | 30.2K |
| Gemini 4 Argon: The New FrontierShort | Oct 1, 2026 | 1:06 | 323.3K |
| Building an Agent Harness with Jev: What Actually Works? | Sep 29, 2026 | 15:33 | 12.2K |
| Qwen 27B on 6GB VRAM... | Sep 28, 2026 | 14:18 | 19.9K |
| 98% of Qwen - Bonsai 2Short | Sep 28, 2026 | 1:06 | 13.7K |
| CLM-8B: Contrastive Language ModelsShort | Sep 27, 2026 | 1:04 | 27.3K |
| This New AI Architecture Makes Decisions 13x Faster | Sep 26, 2026 | 16:29 | 47.8K |
| NVIDIA Nemotron 3 Diarization ExplainedShort | Sep 25, 2026 | 1:12 | 5.1K |
| System 1 vs System 2 AI models: what's actually different?Short | Sep 24, 2026 | 0:59 | 2.5K |
| JEV vs Thinking Models: 100% to 0% | Sep 24, 2026 | 10:37 | 13.5K |
| Opus 5.5 — Anthropic Finally Listened? | Sep 22, 2026 | 9:34 | 30.9K |
| MiMo v2.6: Xiaomi Just Built the Best Open Model | Sep 22, 2026 | 13:05 | 20.6K |
| Your Agent Doesn't Need a Bigger Model | Sep 21, 2026 | 13:15 | 18.6K |
| Build RAG with JEV | Sep 20, 2026 | 11:28 | 47.4K |
| OPEN JEVs are Here! | Sep 19, 2026 | 14:28 | 33.3K |
| Needle 3: You Don't Need an LLM for Function Calling | Sep 18, 2026 | 13:30 | 107K |
| Union Alpha: A Free Model Just Beat Opus 5/GPT-Sol | Sep 17, 2026 | 16:12 | 35.2K |
| DeepSeek V4.1 Flash Is WAY Better Than I Expected | Sep 14, 2026 | 11:45 | 27.2K |
| Why DeepSeek's New Architecture Is a Huge Breakthrough | Sep 13, 2026 | 14:07 | 25.3K |
| TrueForge: Anthropic's Managed Agent Harness, But Open Source | Sep 9, 2026 | 17:44 | 15.9K |
| GPT-6 Astra: The harness matters more than you think | Sep 4, 2026 | 16:47 | 24.9K |
| Gemini 3.8 Flash: The model no one expected! | Sep 2, 2026 | 11:04 | 37.3K |
| Fable 5.1 — Anthropic Finally Listened? | Sep 1, 2026 | 8:16 | 16.9K |
| Qwen 3.8-27B in Deepseek Harness: This Is the Open-Source AI Stack to Beat | Aug 19, 2026 | 14:54 | 55K |
| How to Use Multiple AI Agents in Your IDE | Aug 17, 2026 | 11:01 | 5.8K |
| GLM 5.3: The New Top Open Model! | Aug 14, 2026 | 11:39 | 19.6K |
| DeepSeek Harness - Its a Big Deal! | Aug 13, 2026 | 12:42 | 35.9K |
| Distillation: What Everyone Gets Wrong! | Aug 12, 2026 | 16:57 | 5.3K |
| Build a Local Router with Nemotron Lightning | Aug 11, 2026 | 13:44 | 5.5K |
| Prime-Agent: We've Been Building AI Agents Wrong? | Aug 7, 2026 | 20:08 | 36.8K |
| Qwen Just Did it Again! Open Model Is the NEW Frontier? | Aug 3, 2026 | 11:57 | 11K |
| DeepSeek V4 Flash Locally: 168 GB at 4-Bit, 25 tok/s on Two DGX Sparks | Jul 31, 2026 | 14:02 | 28.3K |
| Can Kimi K3 Beat Opus 5? | Jul 29, 2026 | 10:05 | 4.7K |
| Opus 5 First Impressions: Anthropic Cooked Again! | Jul 24, 2026 | 11:15 | 7.2K |
| Laguna S 2.1 Locally: 118B Coding Model at 80 tok/s on DGX Spark | Jul 24, 2026 | 15:02 | 10.7K |
| This Tiny Engine Makes Huge AI Models Run Locally (Colibri) | Jul 20, 2026 | 12:48 | 7.8K |
| Kimi K3 Explained! | Jul 17, 2026 | 9:28 | 9K |
| Inkling: Why Thinky's Open Model May Change "Everything" | Jul 16, 2026 | 11:22 | 11.5K |
| Bonsai 27B in 3.9 GB: 1-Bit Quantization Explained and Tested | Jul 15, 2026 | 13:38 | 7.9K |
| "Just Go Local" Solves Nothing. Here's What Does | Jul 13, 2026 | 11:45 | 8.5K |
| Diffusion Is Coming for Text. Here's NVIDIA's New Model. | Jul 6, 2026 | 11:22 | 7.7K |
| Stop Building AI Agents the Old Way | Jul 3, 2026 | 14:50 | 6.4K |
| LongCat 2.0: N-Grams Beat More Experts | Jul 2, 2026 | 11:31 | 8.4K |
| Sonnet 5, more expensive than opus? | Jun 30, 2026 | 9:21 | 12.1K |
| Gemini Omni Flash: Anything to Anything model from Google | Jun 30, 2026 | 12:35 | 8.4K |
| Speculative Decoding Explained: DeepSeek DSpark, Tested on a Mac | Jun 28, 2026 | 11:03 | 45.7K |