News for hackers. Stuff that matters.

A comment on Prompt injection explained, with video, slides, and a transcript. Parent comment

Re:Prompt injection explained, with video, slides, and a tra... by spacebanana7 on Saturday May 13, 2023 @03:13PM (#35931673)
> Is it a "nuclear bomb"-type issue?

Given the allure of using AI in the military for unmanned systems it’s not that far off.

With a lesser danger level, similar adversarial dynamics exist in other places where AI might be useful. E.g dating, fraud detection, recruitment

[ Parent | on HN ]
Re:Prompt injection explained, with video, slides, and a tra... by tagyro on Saturday May 13, 2023 @03:22PM (#35931775)
Please don't spread more FUD, no-one is using OpenAI's GPT in the military.

Is GPT perfect? Hell, no?

Does it have biases? F*c yeah, the same ones of the humans that programmed it.

[ Parent | on HN ]
Re:Prompt injection explained, with video, slides, and a tra... by danShumway on Saturday May 13, 2023 @04:17PM (#35932287)
Both Palantir and Donovan are looking to use LLMs in the military: https://www.palantir.com/platforms/aip/, https://scale.com/donovan

This might be technically correct, in the sense that I think these companies have their own LLMs they're pushing? They're not literally using OpenAI's GPT model. But all LLMs are vulnerable to this, so it doesn't practically matter if they're using specifically GPT vs something in-house, the threat model is the same.

[ Parent | on HN ]