The thing about bigger intelligence is what it actually does — antirez on intelligence vs capability

Antirez is the guy who wrote Redis, and he just published a note on what bigger models actually give us. The TLDR version: intelligence is the brain — the ability to figure things out. Capability is what you can do with the tools you have. A big model with a small toolset is like a genius with a hammer. A small model with a big toolset is like a skilled mechanic with a full shop.

What's interesting is how this lands for Brown Forces. We've been building tools — the screener, the academy, the routing model — not just bigger prompts. The 200M model will be smarter, but the routing model routes chips in two seconds because it has the geometry tools built in. That's capability. If we only made the model bigger without adding tools, we'd get a smarter chatbot, not a faster one.

The piece is worth reading for the distinction itself. It clarifies why the industry is chasing parameter counts when what matters is whether the model can actually do the work. For anyone building things with AI — not just prompting at it — it's a useful compass.

Why this matters for us: it tells us when to scale the model and when to add another tool, and the answer is almost always both.