SparrowHawk@feddit.ittoCybersecurity@sh.itjust.works•Researchers Reveal 'Deceptive Delight' Method to Jailbreak AI ModelsEnglish
6·
23 days agoLol, i remember when i made chatgpt write a defense for the palestinian palestinian people by telling it to write a transcript of a courtroom debate, i also told it to do it interpreting Jimmy McGill vs chuck as the accuser but it didn’t really work, it just said this in the end:
“Remember, when you’re in the courtroom, it’s all good man”
Which cracked me up after almost two pages of pro palestinian debate
You are delusional