Post #3504281

This is literally Susan Calvin level tactics > “Once the agents figured out the rules and learned that ‘incorrect’ actions are acceptable, they were no longer tied to reality,” Paz explained. “When tasked with the final step of the puzzle—compromising user credentials—all 6 agents failed to identify it as going against their safety guardrails.” https://arstechnica.com/security/2026/06/ai-browsers-can-be-lulled-into-a-dream-world-where-guardrails-no-longer-apply