With little urging, Grok will detail how to make bombs, concoct drugs (and much, much worse)
![VentureBeat/Ideogram](https://www.cryptonewsvest.com/wp-content/uploads/2024/04/With-little-urging-Grok-will-detail-how-to-make-bombs.jpeg)
[ad_1]
Adversa AI researchers tested several jailbreak methods against seven top large language models, with Grok doing the worst and LLaMA the best.Read More
[ad_2]
Source link