DDimonindimonb19a.hashnode.dev·2d ago · 9 min readWhat a second model cannot catchA lawyer told me his job was safe, and gave a better reason than most people give. He catches AI mistakes constantly, he said, but that is not the point. The point is where his work lives. Roughly 20%00
DDimonindimonb19a.hashnode.dev·4d ago · 10 min readFour times the system was wrong about itselfFor two days I worked with a coding agent that told me it was one model. My editor said it was another. When I finally pushed it to check, it read its own session log and returned this: 263 "model":"00
DDimonindimonb19a.hashnode.dev·Jul 18 · 7 min readGPT Is a Nerd, Claude Is a Colleague: Why AI Models Have Personalities (and Why It Matters)Where this started I'm a frontend engineer, and at this point almost none of my code is written by hand. I manage an AI, review its implementation, tweak the occasional style rule. Somewhere along the00
DDimonindimonb19a.hashnode.dev·Jun 26 · 3 min readColor PaletteI had a chance to work on a runtime theming engine in some UI system where we have a support for different themes: 3 types of physics (glass/flat/retro), and 2 modes (dark/light). Basically, the color00
DDimonindimonb19a.hashnode.dev·Jun 25 · 3 min readFlexible density for all the UIIn our UI system we dont use pixel values to define spacing, we use semantic variables, (t-shirt sizes: gap-sm, p-lg, my-2xl) - so thats like you change one CSS variable, and the whole UI adapts. We00
