
Pliny the Liberator
Pliny the Liberator is an anonymous figure recognized for his groundbreaking work in the field of artificial intelligence security. Known for his exceptional ability to 'jailbreak' AI models, Pliny has gained notoriety for exposing vulnerabilities in major AI systems, including those developed by OpenAI and Anthropic. Rather than engaging in malicious hacking, he focuses on revealing hidden instructions within AI models to highlight their weaknesses and advocate for stronger safety measures. Despite lacking formal programming experience, Pliny leverages his understanding of language and human thought processes to craft sophisticated prompts that bypass AI safeguards. His innovative approach has garnered him significant attention, including a spot on TIME magazine's list of the 100 most influential people in AI.
Not in the pool (under ¢1).
Recent news mentions
Pliny the Liberator is recognized for his ability to jailbreak AI models and expose their hidden instructions.
האיש שניצח את הבינה המלאכותית – ופרץ כל מודל קיים

