←back to thread

The "confident idiot" problem: Why AI needs hard rules, not vibe checks

(steerlabs.substack.com)
323 points steerlabs | 1 comments | 04 Dec 25 20:48 UTC | HN request time: 0.001s | source
Show context
wintermutestwin ◴[08 Dec 25 13:55 UTC] No.46192249[source]▶
Can someone please explain why these token guessing models aren't being combined with logic "filters?"

I remember when computers were lauded for being precise tools.

replies(2): >>46192796 #>>46198343 #
1. mrguyorama ◴[08 Dec 25 22:12 UTC] No.46198343[source]▶
Intellij knows my Frob class does not have a static Blurb method, yet will still allow an LLM to generate a code completion of "frob.blurb()"

It's insanity. This one stupid issue has cost me significant productivity. I got so much benefit from being able to hit "Tab" every few lines, but now I instead have to press whatever button combos or interactions cause the suggestion to go away, and then type what would have been suggested previously.

We had really good code completion that never made this kind of mistake for 20 years. Apparently we are going to throw that all away because """AI"""?

Just utter fucking insanity.