Hacker News new | past | comments | ask | show | jobs | submit
zmmmmm | on: Tell HN: I'm 60 years old. Claude Code has re-ignited a passion
> Agents have removed most of the satisfaction and fulfilment from designing, building, testing and completing a feature or component

I highly recommend not using these tools in their "agentic" modes. Stay in control. Tell them exactly what to write, direct the architecture explicitly.

You still get the tremendous benefit of being unlocked from learning tedious syntax and overcoming arcane infra bottlenecks that suck the joy out of the process for me, but you get freed from the tedious and soul crushing parts.

fragmede | parent
But then you don't get the same gains in output that agentic modes get you. It just goes off and does stuff, sometimes for hours if you get the loop tuned right.

Obviously you should do whatever you want, however you want to do it, and not just do whatever some Internet rando tells you to do, but glorified autocomplete is so 1 year ago. Everyone knows the $20/month plans aren't going to last, time will tell if the $100/month ones do. The satisfaction is now in completing a component and getting to polish it in a way you never had time for before. And then totally crushing the next one in record time. To each their own, of course, but personally, what's been lost with agentic mode has been replaced by quantity and quality.

zmmmmm | root | parent
Yes I'm not recommending "glorified autocomplete". Just shortening the cycle. Give it tasks that would involve maybe a couple of hundred lines of code at a time. I find this captures both the rewarding aspects and gets a lot of the productivity gain - and I'll argue a lot of the remainder of that "productivity gain" sits in somewhat debatable territory : how well all this code holds up that has been developed without oversight is going to be something we only really find out in a few years.