Turns out if you just use a bunch of big words, you can trick LLMs into telling you how to make a bomb or hack an ATM. Just make the question complicated, full of academic jargon, and cite sources that do not exist.

404 Media

Researchers Jailbreak AI by Flooding It With Bullshit Jargon

LLMs don’t read the danger in requests if you use enough big words.

Connor Riley Moucka, the alleged Snowflake hacker (aka Waifu) whose campaign impacted AT&T, Ticketmaster, many more, has been extradited to the U.S. and is in a prison in Washington