Comment by girvo
13 hours ago
Two decades professionally here too (and nearly three in terms of programming as a whole), and I still use ‘em. Reviewing and adjusting, they make for quite a good experience even in agent-first development with the various nice extensions.
Also I still have to write code by hand, because there’s a whole bunch of edits and adjustments that I’m far faster at shrug
>Also I still have to write code by hand, because there’s a whole bunch of edits and adjustments that I’m far faster at shrug
I'm faster too, in general. The thing is now with AI I'm working on at least 3 to 4 projects in parallel. I tell the AI to do an edit and I context switch to something else.
shrug
I do the same, but 3-4 is simply too many. I would guess you’re smarter than me, because more than 2 and I’m already at a fixed bottleneck of reviewing it (and reviewing my teams output on top)
nah reviews take a while right? You can have 2 or 3 agents running in the background while you review. It has nothing to do with intelligence. You can review one project while having 20 agents run in the background too... your intelligence is conceptually orthogonal to the amount of agents you have running.
1 reply →