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 modriano on Wednesday February 15, 2023 @04:42PM (#34811005)
In your scenario, did the script kiddie get control of Microsoft's Bing? Or are you describing a scenario where the script kiddie spins up a knockoff Bing (either hosting the GPT3 model or paying some service hosting the model), advertises their knockoff Bing so that people go use it, those people get into arguments with the knockoff Bing, and the script kiddie also integrated their system with functionality to autonomously hack the people who got into arguments with their knockoff Bing?

Am I understanding your premise correctly?

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by salawat on Wednesday February 15, 2023 @04:55PM (#34811201)
Microsoft is the script kiddies. They just don't know it yet.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by bibabaloo on Wednesday February 15, 2023 @05:44PM (#34811908)
I think the parent poster's point was that Bing only has to convince a script kiddy to to run a command, it doesn't need full outbound access
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by in3d on Wednesday February 15, 2023 @07:08PM (#34812948)
A script kiddie can connect GPT3.5 through its API to generate a bunch of possible exploits or other hacker scripts and auto execute them. Or with a TTS API and create plausible sounding personalized scripts that spam call or email people. And so on - I’m actually purposefully not mentioning other scenarios that I think would be more insidious. You don’t need much technical skills to do that.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by modriano on Thursday February 16, 2023 @07:24PM (#34828869)
Even if any of that were remotely relevant to this conversation about Bing, GPT models don't generate exploits or "hacker scripts", nor do they execute "hacker scripts". GPT models just provides natural language plain text responses to prompts.
[ Parent | on HN ]