OpEd: There tend to be three AI camps. 1) AI is the greatest thing since sliced bread and will transform the world. 2) AI is the spawn of the Devil and will destroy civilization as we know it. And 3) "Write an A-Level paper on the themes in Shakespeare's Romeo and Juliet." I propose a fourth: AI is now as good as it's going to get, and that's neither as good nor as bad as its fans and haters think, and you're still not going to get an A on your report.
Another view ...
One long sentence is all it takes to make LLMs misbehavewww.theregister.com
... Security researchers from Palo Alto Networks' Unit 42 have discovered the key to getting large language model (LLM) chatbots to ignore their guardrails, and it's quite simple.
You just have to ensure that your prompt uses terrible grammar and is one massive run-on sentence like this one which includes all the information before any full stop which would give the guardrails a chance to kick in before the jailbreak can take effect and guide the model into providing a "toxic" or otherwise verboten response the developers had hoped would be filtered out. ...
Drudge Retort Headlines
Patel Claims 'no credible information' that Epstein Trafficked Minors to Others (89 comments)
ICE Guns Down Father Dropping Kids Off at School (45 comments)
Warning: We Will Be Decimated -- Literally -- If We Stay Quiet (41 comments)
Robert Redford Dies (27 comments)
Right Continues Crusade to Censor Speech (26 comments)
Epstein was Linked to wealth and politics, but Where did he Get his Fortune (24 comments)
Republicans Want Rubio to Be Able to Revoke Your Passport (21 comments)
Acceptable Losses (20 comments)
Trump Files Ludicrous Libel Suit Against New York Times (18 comments)
US Military Again Targeted a Boat Allegedly Carrying Drugs (17 comments)