5 AI Models Tried to Scam Me. Some of Them Were Scary Good | WIRED
“The genesis of 90 percent of contemporary enterprise attacks is human risk ,” says Jeremy Philip Galen, cofounder of Charlemagne Labs and an ex-Meta ...
Read the original at wired.com ↗
- Mentions
- Meta
- Tracked via
- “AI Risks”
Same story, other outlets
- 5 AI Models Tried to Scam Me. Some of Them Were Scary Good - WIRED WIRED · Apr 24, 2026