News for hackers. Stuff that matters.

A comment on CriticGPT: Finding GPT-4's mistakes with GPT-4. Parent comment

Re:CriticGPT: Finding GPT-4's mistakes with GPT-4 by orlp on Friday June 28, 2024 @06:30AM (#40819295)
> Every software bug is an example of a computer doing exactly what it was told to do, instead of what we meant.

That is only as long as the person describing the behaviour as a bug is aligned with the programmer. Most of the time this is the case, but not always. For example a malicious programmer intentionally inserting a bug does in fact mean for the program to have that behavior.

[ Parent | on HN ]
Re:CriticGPT: Finding GPT-4's mistakes with GPT-4 by ben_w on Friday June 28, 2024 @06:49AM (#40819379)
Sure, but I don't think that matters as the ability to know what we are even really asking for is not as well understood for AI as for formal languages — AI can be used for subterfuge etc., but right now it's still somewhat like this old comic from 2017: https://xkcd.com/1838/
[ Parent | on HN ]