A team of researchers developed an AI tool specifically trained to jailbreak other AI LLMs like the ones powering ChatGPT and Bard, allowing it to bypass content filters and safety protocols with a 20%+ success rate.
A team of researchers developed an AI tool specifically trained to jailbreak other AI LLMs like the ones powering ChatGPT and Bard, allowing it to bypass content filters and safety protocols with a 20%+ success rate.