News for hackers. Stuff that matters.

A comment on Bing: “I will not harm you unless you harm me first”. Parent comment

Re:Bing: “I will not harm you unless you harm me first” by jstarfish on Wednesday February 15, 2023 @01:22PM (#34808253)
It already has an outbound connection-- the user who bridges the air gap.

Slimy blogger asks AI to write generic tutorial article about how to code ___ for its content farm, some malicious parts are injected into the code samples, then unwitting readers deploy malware on AI's behalf.

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by chasd00 on Wednesday February 15, 2023 @02:15PM (#34809043)
exactly, or maybe someone changes the training model to always portray a politician in a bad light any time their name comes up in a prompt and therefore ensuring their favorite candidate wins the election.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by DonHopkins on Wednesday February 15, 2023 @02:20PM (#34809142)
Hush! It's listening. You're giving it dangerous ideas!
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by wglb on Wednesday February 15, 2023 @04:49PM (#34811103)
Isn't that really the whole point of exposing this and ChatGPT to the public or some subset? The intent is to help debug this thing.
[ Parent | on HN ]