6 comments

  • brookst 3 hours ago

    Wait how is review capacity not increasing? AI review is not a substitute for human review, but it is helpful.

    I’d posit that more code reaching review has already had an AI pass done by the submitter, and then many/most reviewers use AI as a first pass as well. NOT as the sole pass, but to catch obvious stuff.

    I’m very confused by the implied claim that review capacity per developer is unchanged.

  • davydm 3 hours ago

    yep, this is why people just chuck Claude reviews on my PRs, and why I bothered to set up sandboxing for Claude, so I can make the agent run a review before I take it to PR, so that at the very least, I can add commentary that steers Claude away from bad assumptions when it doesn't seem to understand the business domain, or how things are generally done. Tho, to be fair, it's also found some nifty edge cases in review, so there is some value there - things just fall over when someone can't be arsed to do more than point claude at it and copy-paste the results to the PR. And the people who were bad at review before (ask stupid questions, fight about stuff they don't understand) are just as annoying now, but they feel vindicated because they got Claude to do it, and they will take no responsibility for the time they waste (not that they ever did).

  • rafalgraniczny 4 hours ago

    [flagged]