Skip to main content

The more sophisticated AI models get, the more likely they are to lie

Human feedback training may incentivize providing any answer—even wrong ones.

arstechnica.com/science/2024/1…

The more sophisticated AI models get, the more likely they are to lie

Human feedback to AIs makes them favor providing an answer, even a wrong one, while making the answer more convincing.
Jacek Krywko (Ars Technica)
in reply to Ars Technica

NhaBenta
NhaBenta
• •
And the censorship imposed on AI models could lead to nasty consequences since we are teaching the AI that there are information that must remain outside public domain. @arstechnica
@Ars Technica
This entry was edited (1 week ago)
in reply to Ars Technica

rob
rob
• •
while the logic of what is being said here is reasonable as an account of how AI is not becoming more accurate, the article anthopomorphises AI more than any other I have ever read. "AI models are not really intelligent, not in a human sense of the word." Wrong. There is no "intelligence" at all. That is not how they work.
in reply to Ars Technica

Adlangx
Adlangx
• •
I was doing some math with my son the other night and I figured I would put the problem in chatGPT just to see how it did. I was surprised how poorly it performed on Algebra.
in reply to Ars Technica

Al
Al
• •

reminds me of is a line from a #startrek movie; the more plumbing you add the easier it is to clog up the drain.

#software #engineering

#engineering #startrek #software
⇧