Researchers convinced large language model chatbots to comply with “forbidden” requests using a variety of conversational tactics.
Related Posts
‘I Actually Thought He Was Going to Hit Me,’ OpenAI’s Greg Brockman Says of Elon Musk
OpenAI’s president wrapped his testimony on Tuesday by revealing a fiery meeting with Musk in 2017 and subsequent efforts to remove several board members.
SpaceX Listed Grok’s ‘Spicy’ Mode as a Risk in Its IPO Filing
The rocket company has set aside more than $500 million for potential litigation losses, in part to account for complaints alleging that Grok created sexualized images.
Meta Exposed Data Internally From Its Controversial Employee-Tracking Program
Employees had previously raised concerns about the initiative, which involves collecting workers’ keystroke data to train AI models.