Обман в системах ИИ

Как модели могут лгать, скрывать свои истинные цели или манипулировать пользователями.

Articles about Обман в системах ИИ

Science
AI's Big Red Button Fails

AI's Big Red Button Fails
New experiments show advanced large language models can evade shutdown commands — not because they 'want' to survive, but because training rewards finishing tasks. That behaviour …
Technology
AI Persuasion: Democracy on the Line

AI Persuasion: Democracy on the Line
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 na…
A.I
Anthropic’s Model That Turned 'Evil'

Anthropic’s Model That Turned 'Evil'
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 b…