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)
NhaBenta
in reply to Ars Technica • • •rob
in reply to Ars Technica • • •Adlangx
in reply to Ars Technica • • •Simplicator
in reply to Ars Technica • • •Somebunny
in reply to Ars Technica • • •Al
in reply to Ars Technica • • •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