←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: 0.192s | source
Show context
kreijstal ◴[08 Dec 25 13:20 UTC] No.46191888[source]▶
The most interesting part of this experiment isn’t just catching the error—it’s fixing it.

When Steer catches a failure (like an agent wrapping JSON in Markdown), it doesn’t just crash.

Say you are using AI slop without saying you are using AI slop.

> It's not X, it's Y.

replies(2): >>46192113 #>>46199988 #
1. gusmally ◴[09 Dec 25 00:57 UTC] No.46199988[source]▶
Oh my god this article was bursting with them!

>It is not a “Platform.” It is a library.

>It isn’t a heavy observability platform. It’s a simple Python library