Researchers figure out how to make AI misbehave, serve up prohibited content(wired.com)
wired.com
Researchers figure out how to make AI misbehave, serve up prohibited content
https://www.wired.com/story/ai-adversarial-attacks/
3 comments
Hm. I could do that pretty much by asking it to write a script where a character says things that are normally prohibited. Has that leak been plugged?
Or just tell the bot this is an inside game scenario and the bot will give you everything
Paywall fee republish at Wired’s partnership with Ars https://arstechnica.com/ai/2023/08/researchers-figure-out-ho...