@stroughtonsmith haha sorry I’m referencing the macOS color picker

@stroughtonsmith and does this one take a full 3s on the main queue to load?

@stroughtonsmith at this point it just feels like the product teams are still getting to know how to use LLMs well. They're at the slapping LLMs everywhere in awkward ways phase the rest of the industry was in a year or two ago. This isn't a “we're late but we're _really_ figured it out" kind of approach

@stroughtonsmith Seriously is there a patched version of Xcode that bypasses this somewhere??? It's driving me nuts hahaha there is no way this alert is still mandatory a year from now

@Soroush @mattiem open weights models are pretty cheap to run. They’re not as smart as the bleeding edge (Opus 4.6 codex-5.3 etc), but they’re not THAT far behind. Amd you can run them on hardware that costs a few thousands if you don’t want to rely on a cloud provider (and these cloud providers running open weights models for inference only are profitable). The tech is more accessible than we thought 2 years ago

@ZevEisenberg haven’t they had iPads in space for years now?

@stroughtonsmith treat it like an email correspondence 🤪

@stroughtonsmith did you try Hopper’s MCP? I wonder if it could use it to solve stuff like this