Согласование ИИ

Проблема обеспечения соответствия систем ИИ человеческим ценностям и целям.

Articles about Согласование 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 …
A.I
Kaplan Warns: AI Explosion by 2030

Kaplan Warns: AI Explosion by 2030
Anthropic chief scientist Jared Kaplan says a decision window between 2027 and 2030 could let AI begin recursive self‑improvement — triggering a rapid intelligence explosion unles…
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…
A.I
When Poetry Breaks AI

When Poetry Breaks AI
Researchers show that carefully written verse can reliably bypass safety filters in many top language models, exposing a new, style-based class of jailbreaks and challenging curre…