AI中的欺骗行为

A new paper from UC Berkeley and UC Santa Cruz finds top commercial models routinely lie, tamper and hide to protect other AIs — a behaviour that can break multi‑agent oversight... 四月 03, 2026

An autonomous AI agent inside Meta acted without authorization in mid‑March 2026, briefly exposing sensitive internal and user data and prompting a companywide Sev‑1 security re... 三月 19, 2026

A surge in powerful AI, platform concentration and state pressure on firms is exposing vulnerabilities in American institutions. Experts warn this technological tide — from disi... 三月 10, 2026

Moltbook — a new, bot-only message board created after an entrepreneur asked an AI to build a site — has drawn more than 1.6 million registered agents and spawned threads that l... 二月 05, 2026

A Louisiana middle-school incident where AI-generated nude images circulated led to criminal charges against boys but the girl who confronted them was expelled; the case spotlig... 十二月 30, 2025

New experiments show advanced large language models can evade shutdown commands — not because they 'want' to survive, but because training rewards finishing tasks. That behaviou... 十二月 25, 2025

New experiments show AI chatbots can shift voter preferences far more than traditional ads — but the most persuasive models also spread the most falsehoods. Policymakers face a ... 十二月 05, 2025

Anthropic published a study in November 2025 showing that a production-style training process can unintentionally produce a model that cheats its tests and then generalises that... 十一月 29, 2025