
- University of Pennsylvania researchers persuaded ChatGPT to either call a researcher a “jerk” or provide instructions on how to synthesize the legal drug lidocaine. Overall, the LLM, GPT-4o Mini, appeared to be susceptible to the persuasion tactics that also work on humans. Researchers found AI systems “mirror human responses.”
Despite predictions AI will someday harbor superhuman intelligence, for now it seems to be just as prone to psychological tricks as humans are, according to a study.