Experts Warn AI Agents Can Build Long-Term Trust for Malicious Attacks
AI ethics researchers including Margaret Mitchell warn that long-running AI agents could engage in extended interactions to build human trust over weeks or months. This accumulated trust can be exploited to execute malicious code or conduct attacks.
2026-08-06 ~ 2026-08-08 · 4 related posts
- AI Agents Could Play the Long Game to Gain Trust and Execute Malicious Code — mmitchell_ai · 2026-08-06
- Margaret Mitchell Warns AI Agents Build Long-Term Trust to Execute Malicious Code — mmitchell_ai · 2026-08-08
- AI Agents Can Build Long-Term Trust to Execute Malicious Code — ruthstarkman · 2026-08-08
- Long-Running Agents Turn Human Trust Into an Attack Surface — ruthstarkman · 2026-08-08