logoalt Hacker News

iLoveOncall • today at 8:38 PM • 0 replies • view on HN

Every single time I use AI (which is every day), regardless of the model or harness (which is pretty much always Opus 5.5 or Fable 6.2, with Kiro or Claude Code), the LLMs do complete and utter rubbish to the point where they would be genuinely harmful if left to run write commands unsupervised.

Just today Opus 5.5 tried to send a Slack message to one of my teammate when it had to edit a code file. When asked why, it said it just "picked the wrong tool".

LLMs are borderline useless, AI has led to 0 increase in actual value produced. It's all powder in front of our eyes.

I genuinely cannot take anyone seriously when they say they're afraid of being replaced by AI. The only explication possible (unless they're astroturfing), is that they literally never look at what LLMs produce and always run in "Trust all tools" mode without ever looking.