FeedDiscussion
Really enjoyed this perspective. I especially liked the emphasis on boundaries as it is easy to focus on how much faster AI can help us write code, while overlooking the importance of knowing where it shouldn’t be making decisions for us.
Kartik N V J K
AI Developer | Making AI reliable, trustworthy & accessible to everyone | Active community contributor
The throughput framing is the one I'd push back on too: speed of turning a ticket into code says nothing about whether the change was safe to make. The boundary that matters most in my experience is scope, telling the agent which files and which operations are off limits, so a small task cannot quietly refactor half the repo. Where do you draw the line, at the tool level or with review gates on the diff?