• 27,000 Tokens Before Hello: The Agent Harness Tax 04/14/2026
• Gemma 4: Everything You Need to Know About Google's Most Capable Open Model 04/06/2026
• Embeddings are beautiful. 03/26/2026
• TurboQuant: The cheat sheet that ate your GPU (and how Google fixed it) 03/25/2026
• Doc-to-LoRA & Text-to-LoRA: How Sakana is teaching LLMs to learn instantly 03/01/2026
• BlinkThink: Self-Hosted Camera Snapshots with FastAPI and Gemini 02/26/2026
• Building a Browser Agent with Gemini and Playwright 02/15/2026
• The 10-Million Token Paradox: Decoding the Logic of Recursive Language Models 02/08/2026
• OpenClaw: 98% Plumbing, 2% Revolution 02/08/2026
• VerbalVista: Talking to Your Own Data with RAG, FAISS, and a Bit of Stubbornness 02/15/2025
• Exploring Model Quantization for LLMs 05/01/2024