Get the latest tech news

Major AI models are easily jailbroken and manipulated, new report finds

Easily jailbroken models show safeguards are failing.

Researchers used prompts in line with industry standard benchmark testing, but found that some AI models didn't even need jailbreaking in order to produce out-of-line responses. The investigation also assessed the capabilities of LLM agents, or AI models used to perform specific tasks, to conduct basic cyber attack techniques. On May 18, OpenAI CEO Sam Altman and president and co-founder Greg Brockman responded to the resignations and growing public concern, writing, "We have been putting in place the foundations needed for safe deployment of increasingly capable systems.

Get the Android app