News for hackers. Stuff that matters.

A comment on GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2. Parent comment

Re:GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2 by coldtea on Sunday June 21, 2026 @08:56AM (#48618548)
>I have a theory- LLMs can spit out code that gets the job done and looks ok, maybe even great, but contains small “anomalies” that compound over time. An enterprise app developed entirely with LLM-happy devs might end up virtually unmaintainable.

For most enterprise apps, being "unmaintainable" would be an improvement.

[ Parent | on HN ]

There are no comments on this comment yet.