Field notes from people tinkering through the AI transition - built by hand, in their own backyards, on the projects they actually care about. We're all building this.https://ourweirdfuture.dev/https://ourweirdfuture.dev/posts/three-layers-of-ai/https://ourweirdfuture.dev/posts/three-layers-of-ai/AI improves at three layers. Two are locked behind billion-dollar labs. The third, figuring out what to do with the models that already exist, is wide open, and the people poking at it in their own hobbies are quietly mapping the jagged frontier of what these things can actually do.Sat, 04 Jul 2026 00:00:00 GMThttps://ourweirdfuture.dev/posts/tuning-llama-server-for-agents/https://ourweirdfuture.dev/posts/tuning-llama-server-for-agents/A 4090 can run a 35B MoE at agent-useful speeds. But the difference between the default config and a tuned one is 80x, and the difference between two GGUFs of the same model is 200x.Wed, 13 May 2026 00:00:00 GMThttps://ourweirdfuture.dev/posts/borrowed-from-everywhere/https://ourweirdfuture.dev/posts/borrowed-from-everywhere/Innovation has always been recombination: patterns lifted from one field and dropped into another. An LLM already contains every field. The trick is making it actually reach.Wed, 13 May 2026 00:00:00 GMThttps://ourweirdfuture.dev/posts/what-this-blog-is-actually-about/https://ourweirdfuture.dev/posts/what-this-blog-is-actually-about/I thought I was building a chicken coop monitor. Turns out I'm running a long-running experiment in applied AI, and the chickens are the case study.Sat, 11 Apr 2026 00:00:00 GMT