Re:Microsoft 365 Copilot – Arbitrary Data Exfiltration via M...
by narrator on Sunday October 26, 2025 @09:29PM
(#45716490)
Prompt Injection is an interesting difference between human consciousness and machine "consciousness", or what people try and liken to it. A human can easily tell when information is coming from his memory or internal thoughts and when it is coming from a possibly less reliable outside source. Gaslighting is essentially an attempted prompt injection and is considered psychological abuse. Interestingly, people complain about AI gaslighting them and AI doesn't seem to think that's a problem.
[ Parent
| on HN ]
Re:Microsoft 365 Copilot – Arbitrary Data Exfiltration via M...
by lazyasciiart on Sunday October 26, 2025 @09:58PM
(#45716641)
Isn’t that what marketing is?
Re:Microsoft 365 Copilot – Arbitrary Data Exfiltration via M...
by chasing0entropy on Sunday October 26, 2025 @11:10PM
(#45717040)
Zing. I was about to remark on the fascinating paradigm of AI emotionally abusing humans without consequence but now the rabbit hole has deepened to considering what level of advertising could also be justified as emotionally abusive and how many layers of legislative protection may already exist to pre-empt the argument.
Re:Microsoft 365 Copilot – Arbitrary Data Exfiltration via M...
by mrasong on Monday October 27, 2025 @01:26AM
(#45717671)
We're going to see a new kind of hacker — prompt-injection attacks.
Re:Microsoft 365 Copilot – Arbitrary Data Exfiltration via M...
by MattPalmer1086 on Monday October 27, 2025 @05:20AM
(#45718845)
We already have.