Researchers at Palo Alto Networks’ Unit 42 have discovered a new AI jailbreak technique known as “Bad Likert Judge,” which manipulates large language models (LLMs) to bypass safety measures. The atta…
Substack is the home for great culture
Researchers at Palo Alto Networks’ Unit 42 have discovered a new AI jailbreak technique known as “Bad Likert Judge,” which manipulates large language models (LLMs) to bypass safety measures. The atta…