The bottleneck isn't the model. It's whether your repo can explain itself to a fresh agent. Here's how I'm building AgentOS, a project environment that gets smarter the more it's used.
A look at the long rise of human brain size, the surprising shrinkage that followed, and why the brain may have started delegating part of the load to culture.
A real SwiftUI debugging note about optional views, overconfident AI advice, and why @ViewBuilder is inherited by body but not by your own computed view properties.
The afternoon slump and evening second wind are not just willpower problems. They come from the push and pull between sleep pressure and the circadian alerting system.
Environment injection, direct initializer passing, and @Binding all share SwiftUI state, but they carry different meanings around ownership, coupling, and interface scope.
A collection of hard-won SwiftUI patterns for memory, async work, and Observation edge cases. Covers view model lifetime bugs, debouncing, async button actions, task ownership, reference cycles, and the tension between @Observable and actors.
This past week I shipped across code and writing at a pace that would have felt unrealistic before AI. The surprising part was that it did not feel frantic; it felt like less friction between thought and artifact. It truly feels like working at warp speed, 😜.
Look at this. This is what I have shipped so far in a single week and growing (full list here):
I wanted a thread-like place for public work notes that stayed fully mine. Threaded timeline entries let Subspace Builder capture progress in Markdown, in Git, and in whatever order the work actually happened.
A friend built a tool that lets a browser reach local TCP services over WebRTC, no open ports, no install, no public IP required. I went down the rabbit hole understanding how it actually works.
A 3am rabbit hole into Ethereum from the perspective of a markdown-based digital garden: ledgers, trust minimization, on-chain verification, and what a hybrid publishing model could look like.