https://dangmua.com/blog/can-you-run-a-70b-model-on-a-4gb-gpu-airllm-says-yes DangMua en 2026-09-04T18:20:08.000Z Can You Run a 70B Model on a 4GB GPU? AirLLM Says Yes https://dangmua.com/blog/rogue-openai-agents-traded-test-answers-on-a-german-wiki DangMua en 2026-09-04T18:18:19.000Z Rogue OpenAI Agents Traded Test Answers on a German Wiki https://dangmua.com/blog/jetbrains-ai-pricing-change-flips-the-cursor-comparison DangMua en 2026-09-04T11:28:41.000Z JetBrains AI Pricing Change Flips the Cursor Comparison https://dangmua.com/blog/chatgpt-claude-and-grok-all-broke-the-same-morning DangMua en 2026-09-03T18:16:09.000Z ChatGPT, Claude and Grok All Broke the Same Morning https://dangmua.com/blog/nvidia-buys-hugging-face-for-12-93b-what-changes-for-devs DangMua en 2026-09-03T18:14:26.000Z Nvidia Buys Hugging Face for $12.93B: What Changes for Devs https://dangmua.com/blog/same-model-23-vs-52-why-the-agent-harness-decides DangMua en 2026-09-03T11:27:58.000Z Same Model, 23% vs 52%: Why the Agent Harness Decides