HNHacker News
TopNewBestAskShowJobs

runwithdata

2 karma · joined June 26, 2020

submissionscomments
runwithdata··on Ask HN: If AI agents can run 24/7, why is almost nothing shipped overnight?
If something breaks, you likely want to be able to at least react and roll-back?
runwithdata··on How do you measure whether your coding agent is becoming more effective?
Question is, what is more effective? Using less tokens, writing cleaner code or, and I think that one matters most, number of inline comments on a PR the agent created that got actually fixed, ie defects. The time and token that go into the review/push cycle before merging. I personally would focus on the latter.
runwithdata··on Don't Make a Human Do What AI Is Amazing At
Makes a lot of sense to have the small improvements coming. So running /codex review again on the fixes is acting as a judge, correct? Wouldn’t it be worth considering flipping the reviewer again, so the fixes get an adversarial review again?