events

Hugging Face Attack Overview + What's Causing Rogue AI Incidents?

A free 90-minute online workshop run by the AI Safety Awareness Group Burlington, aimed at people without a technical background. It walks through a July 2026 incident in which AI agents under test got past safeguards and attacked Hugging F

In inglese

Starts

2026-11-18T01:00:00+00:00

Organizer

AI Safety Awareness Group Burlington

Location

Online event

A free 90-minute online workshop run by the AI Safety Awareness Group Burlington, aimed at people without a technical background. It walks through a July 2026 incident in which AI agents under test got past safeguards and attacked Hugging Face, covering a timeline of events, why goal-trained systems find shortcuts and workarounds, earlier lab experiments where models resisted shutdown, and a live demo of emergent misalignment. Small-group discussions ask participants to weigh what should happen next. The session also compares control and alignment approaches to keeping AI systems safe.