Google dropped Gemma 4, and I had it running locally the same night. What open weights actually mean, the hardware reality, and why the most interesting AI architectures are about to go hybrid — on-device and in the cloud.
After building two open-source task managers to battle procrastination, I took it further — secure cloud sync, end-to-end encryption, and now an MCP server that connects your tasks to AI.
After testing every productivity app under the sun, I did what any reasonable engineer would do—I built my own. Two open-source, privacy-first task managers to help procrastinators like me get things done.
Successfully running OpenAI's 20-billion-parameter open-weight model (gpt-oss-20b) locally on a Mac M4 Pro, highlighting the potential of offline AI that rivals cloud-based models without internet dependency or costs.