News for hackers. Stuff that matters.
Re:An AI agent coding skeptic tries AI agent coding, in exce... by prateekk77 on Monday March 02, 2026 @08:18AM (#47217632)
"Your codebase must be bad" is backwards. Agents perform better on well-structured codebases with clear interfaces and good tests. They struggle on legacy spaghetti.

The mental model that works: treat them like junior engineers. Clear issue, bounded scope, review their PR. Output quality tracks directly with task scoping.

Where it genuinely falls apart: anything requiring context about why something was designed a certain way. Agents can read code, they can't read the Slack thread from 2023.

There are no comments on this comment yet.