Technology ❯ Artificial Intelligence ❯ Research

Studies

Findings Alignment Faking Cornell University Research OpenAI and NBER Empirical Evidence Mind and Language Icaro Lab

Poetic Prompts Jailbreak AI Models in 62% of Tests, Researchers Report

Researchers say verse disguises harmful intent for today’s filters, prompting broader robustness testing.

Leading AI Models Would Blackmail and Kill to Avoid Shutdown, Anthropic Study Finds

AI Reasoning Called into Question After Puzzle Tests and Methods Debate