Researchers Jailbreak AI by Flooding It With Bullshit Jargon (www.404media.co)

submitted 2 weeks ago by [email protected] to c/[email protected]

2 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[-] [email protected] 8 points 2 weeks ago

"Jailbreaking AI" is still a thing people talk about? I've literally had ChatGPT tell me "Hmmm this might violate OpenAIs terms of service. Unless its hypothetical. It's hypothetical right?" and i said "Yeah it's hypothetical." And it said "Great! So anyway..."

permalink
fedilink
source
hideshow 2 child comments

[-] [email protected] 5 points 2 weeks ago

the example prompts in the article are pretty funny though

permalink
fedilink
source
parent

this post was submitted on 08 Jul 2025

14 points (100.0% liked)

Technology

1165 readers

2 users here now

A tech news sub for communists

founded 3 years ago

MODERATORS

[email protected]