Instead of writing Pi you can write:
E(E(E(1,E(E(1,E(1,E(E(1,E(E(1,E(E(1,E(1,E(E(1,1),1))),1)),E(E(E(E(E(1,E(E(1,E(1,E(E(1,E(E(E(1,E(E(1,E(1,E(E(1,1),1))),1)),E(E(1,E(E(1,E(E(1,E(E(1,1),1)),E(E(E(1,E(E(1,E(1,E(E(1,1),1))),1)),E(1,1)),1))),1)),1)),1)),1))),1)),E(E(E(1,E(E(1,E(1,E(E(1,1),1))),1)),E(E(1,E(E(1,E(1,E(E(1,E(E(1,E(E(1,E(1,E(E(1,1),1))),1)),E(1,1))),1))),1)),1)),1)),1),1),1))),1))),1)),E(E(E(1,E(E(1,E(1,E(E(1,1),1))),1)),E(E(1,E(E(1,E(1,E(E(1,E(E(1,E(E(1,E(1,E(E(1,1),1))),1)),E(1,1))),1))),1)),1)),1)),1)
This has to be a wind up
@bcherny@zeeg@bcherny are there any known token consumption issues with Opus 4.6? I've noticed recently that i'm burning through credits within an hour or two, even on the max plan
@yacineMTB I think it boils down to Claude being able to understand the developers needs better than GPT. If the needs are explained perfectly then GPT tends to do an equally / better job
@matterasmachine@Patriot5715 If a particle is going left at c and it emits a particle right at c, you think the particle emitted right will also be c?
A neutral observer will see one particle going left at c, and one going right at c?