News

How Basic Persuasion Can Bypass AI Safeguards

  • Gloria Yuen--Upenn.edu
  • published date: 2026-06-29 18:41:08 UTC

New Wharton research suggests AI models may be vulnerable to many of the same persuasion tactics that influence people.…Read More

Concerns over jailbreaking AI a way of circumventing the safety guardrails built into large language models have escalated after the Trump administration ordered Anthropic to pull its latest models, … [+4406 chars]