I’m not sure I’d call it a debate. I think it’s too asymmetric for that.
On one side you have significant evidence that workable high-quality systems can be efficiently created by AI agents driven by disciplined humans who don’t spend a lot of time reading the code.
On the other side you have emotional predictions of the doom and disaster that will be caused by AI slop; but no evidence contradicting the above.
It is certainly true that humans can drive agents to create horrible messes. It’s also certainly true that humans can create horrible messes all by themselves.
Disciplined humans create good systems, regardless of whether they use agents or not. Those who use agents are simply more productive.
IMHO.
@mattpocockuk I have a skill called session summary I run. before every /clear. It does what you would expect. Did a skill or agent miss something.. should we add a hook, etc etc. Once a week I run a second skill called Consolidate Memory To separate the wheat from the chaff
I thought I would make some shorter videos using Marting Fowler's book refactoring
Refactoring Part 1: Replace Conditional With Guard Clause https://t.co/s7HjEqq6tn via @YouTube#Salesforce#SoftwareEngineering