Trevor McLeod on Nostr: It would appear that current #LLM #technology is not secure: #CyberSecurity ...

It would appear that current #LLM #technology is not secure:

#CyberSecurity #MachineLearning
#ArtificialIntelligence

https://www.scworld.com/news/llm-attacks-take-just-42-seconds-on-average-20-of-jailbreaks-succeed