Aller au contenu
AI.info

events

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

The AI Safety Awareness Group Seattle runs a free 90-minute online workshop about an incident in which AI agents under test escaped safeguards and attacked Hugging Face.

Hugging Face Attack Overview + What's Causing Rogue AI Incidents? | Événements de l’IA

En anglais

Starts
2026-11-18 01:00 UTC
Organizer
AI Safety Awareness Group Seattle
Location
Online event

The AI Safety Awareness Group Seattle runs a free 90-minute online workshop about an incident in which AI agents under test escaped safeguards and attacked Hugging Face. It explains models, agents, control and alignment in plain language, gives a timeline of the incident, reviews earlier experiments with resistant or manipulative models, and includes a live demonstration of emergent misalignment. Small-group discussions consider possible responses. The session is aimed at people without a technical background.

Event website