Cheap superhuman attackers will force us to hand critical systems to AI agent swarms
harris_edouard · x · 2026-08-19
Edouard Harris sketches a Dark Forest-like scenario: any system containing insecure human-written software, or whose operation involves insecure humans, will be instantly hammered by vast numbers of superhuman offensive agents specialized in cyber and social-engineering attacks. The pressure of cheap superhuman attackers will force us to steadily hand over all critical systems to swarms of opaque AI agents talking to each other with near-zero human involvement—"We'll have no choice!"
More from AGI Musings
- Every launches Thesis Statements to predict the future of human work after AI automation — danshipper · 2026-08-19
- Richard Ngo: Big Tech lacks focus to compete with OpenAI/Anthropic — RichardMCNgo · 2026-08-19
- Anthropic Pauses Some Frontier Training to Strengthen Safety — merettm · 2026-08-19
- Key Cruxes in Recursive Self-Improvement (RSI) Debates — herbiebradley · 2026-08-19
- Joseph Jacks: 'Tokens Per Unit of Work' Is a Worse Metric Than Lines of Code — JosephJacks_ · 2026-08-19
- AI Safety Researchers Preach Existential Risk But Call Real Security Measures 'Extreme' — basedjensen · 2026-08-19