Post

Skill issue.

Dan Tappan@dantappan.net

Cory Doctorow describes what has been my thesis about “AI” coding: it’s great for small productivity projects, it’s a source of crippling tech debt for production code and libraries.

Accurate that it's a skill issue. Why is being a bit flippant about it but it's accurate. Good engineers know how to get good work out of llms; bad ones produce tech debt. Same as ever

lol I know you're joking but it's been weird how often people seem to think talent and experience aren't still a factor Like, in both directions: 1, rookies don't need to know what you're doing anymore, and 2, experienced engineers aren't capable of evaluating whether AI coding is good or not

It'll be really interesting once we figure out exactly what the divide is between people who can't get good output from coding agents and those who can Because it's not "the people getting good output are idiots shilling technology" nor is it "the people getting bad output are just dumb"

Like is there something in the way those with a negative experience are prompting? Are those who are getting better output just less prescriptive with their evaluation? Like I prompt like I'm talking to a coworker, are others prompting like they're talking to a machine doing their bidding?

Heh yeah probs I mean, when we evaluate candidates now it's almost entirely about the depth of knowledge. We watch them write prompts and it's like peering into their brain. How well people understand the engineering principles at play seems determinant

0 reposts11 likes

No replies yet.