All of these agent wrappers/claws/whatever seem to encourage wildly irresponsible usage of AI. Sure it can get stuff done in what is effectively a simple loop but without review we’re just playing with fire.

I was experimenting with Claude code doing similar (don’t need wrappers really) and the result was a huge amount of mediocre code and my weekly limit burnt. The code “works” but oh my the duplication and potential bug surface is off the chart.

Stopped my experiment and back to human in the loop plan->execute cycle which is way more effective.

Thankfully I don’t think we’re at jarvis levels yet.