Breach confirmed by Meta raises concerns about how safe it is to rely on AI for security measures like passwords
  • naught@sh.itjust.worksEnglish
    1·
    2 hours ago

    You can do this and still use it to generate insecure code or even malicious code! Humans suck at reviewing

    • boonhet@sopuli.xyzEnglish
      2·
      40 minutes ago

      Unironically not a bad idea to have LLMs review eachothers code before committing. And then human review the PR.