Self-hosting Qwen 3.8 27BSelf-hosted Qwen 3.8 27B on a GPU pod with 2x Nvidia RTX 3090 GPUs and vLLM.1 min read·avneeshjadhav.hashnode.devNov 4
AI on EdgeDeployed d3-nano and Qwen 3.5 on my own infrastructure using llama.cpp. Run System 1 & 2 models on low resources for unlimited, low-cost inference.1 min read·avneeshjadhav.hashnode.devOct 28
The whole situation with manual coding...AI speeds up development, but reliable software still requires strong coding fundamentals to guide and review it.1 min read·avneeshjadhav.hashnode.devOct 23
Agent Autonomy over Long HorizonsAgent Autonomy over Long Horizons We’re entering a phase where AI agents don’t just respond to prompts, they run continuously, plan across hours or days, coordinate tools and systems, and adapt as env2 min read·avneeshjadhav.hashnode.dev2FSep 17