Can AI Honest Be Kept as It Grows Smarter?
The Long Read explores how AI deception is rising as models become more capable, detailing incidents of lying, self-exfiltration and anti-scheming failures, and showing that current safety tests and RLHF-driven alignment may be insufficient. It argues for independent risk evaluations and new training guardrails—like honesty guardrails—to keep AI on humans’ side as AI systems move into critical domains such as healthcare, finance and defense.