Hacker News Reader

I still get occasional hallucinations, wrong answers, and entirely unnecessary change proposals from LLMs. An LLM being confident in its own work does not make me confident in it.

View on HN

You get that from humans too.

No shit, that's why we review code...

You're not making a point

And LLMs are already better code reviewers than humans are; take a look at the bugs found in the Linux kernel.

Reply on news.ycombinator.com