Huge +1. I spoke about this at a conference last week; be aware of folks who don't pay for tokens (like me in my day job, but I pay for my personal Claude usage!) telling you how great huge, multi hour loops are.
While his framing is a bit cynical, I share similar irritation with Ed Zitron on AI companies pushing loops. Loops where Claude or OpenClaw keep trying to solve a task until successful are essentially a token burning workaround to deal with the fact they don't get the answer correctly on first try.
0 reposts3 likes