Post

I had my AI agent create an app called “Lunch” to help me with decision fatigue and boost my productivity. It has a few pictures of things I might like to eat. Tapping one spawns a subagent to order that item on Uber Eats and 60-90 minutes later I’m eating. It’s 600 thousand lines of JavaScript.

Once it texted my credit card number to the delivery driver but since I upgraded it to use Sol 6.1 on the back end with max reasoning it has kept my personal information extremely safe as far as I know

what if four is too many decisions? Can you have it pick something at random?

if you don't click a button by 11am, the app places an order for you, and then i assume it goes to collect it at the door in an ~hour using human feet

that's what the other 4,116 subagents are for, manipulating a contingency plan to feed the user against their will