Cursor rebuilt SQLite for $1,339 using Composer 2.5 and Opus 4.8, versus $20,000 with other models. A frontier model decomposes tasks into worker agents. Fable 5 initially generated 64,000 lines of code, but an agent-swarming meta layer cut it to 9,900 lines.
Cursor rebuilt SQLite 6 different ways, and the costs ranged from $1,339 to over $10,000 on the same exact task. One of the cool things was this cost to rebuild SQLite by model mix. So you could see Opus 4.8 running tests again on Opus 5.5 as of this podcast recording would be interesting, but Opus 4.8 as the sort of brain of the operation, and then Composer 2.5 ended up building SQLite at $1,339. And when you look at the very right on the spectrum in terms of cost and efficacy, we have Fable 5 just YOLOing it at about $20,000. Right before that, GPT-5.5 at $10,000. So the architecture here was really frontier model plans, worker agents execute. And the frontier model decomposes the goals in these autonomous goal loops. And on the Fable 5 config, the old swarm wrote about 64,000 lines. And when they introduced this agent swarming meta, the new swarm wrote 9,900 lines for the same task, which is really interesting because I know Hamel and I have talked about how there's a lot of verbosity and slop that comes with AI coding agents. And that's like a tension point where in a clean architecture, it's not like you want more code all the time. You do want to slim down your code, make it more elegant and refactor.
