‹ BackHN Continuity

Thread

The Four Horsemen of Agentic Coding

114 points · 89 comments · haute_cuisine

  1. natino · · focus · HN ↗
    I'm a senior software engineer at my company. The AI slop is so bad that it's causing myself code review fatigue. The engineers are also intermediate with 3-4 years of experience.I had one guy report me to his manager because I wasn't letting him merge his PR in because of a critical bug with his code that his precious ai didn't understand.
    1. ActionHank · · focus · HN ↗
      We're already at the stage of "code reviews are slow, we should have the agents do code reviews".
      1. kenhwang · · focus · HN ↗
        My previous employer even suggested code reviews are for human code only, AI-only code can go out without review as long as CI passes since the AI can be prompted to review its own code before committing.
        1. ActionHank · · focus · HN ↗
          Even better if ai writes the tests.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.