david_senate, 4 months ago to OpenAI "A good first step in understanding the threats posed by unsecured AI is to ask secured AI systems like ChatGPT, Bard, or Claude to misbehave." https://spectrum.ieee.org/open-source-ai-2666932122 #OpenAI #AI #chatgpt #bard #Mistral #StabilityAI #Eleuther #AIAct #cybersecurity #security
"A good first step in understanding the threats posed by unsecured AI is to ask secured AI systems like ChatGPT, Bard, or Claude to misbehave."
https://spectrum.ieee.org/open-source-ai-2666932122
#OpenAI #AI #chatgpt #bard #Mistral #StabilityAI #Eleuther #AIAct #cybersecurity #security