AI security veteran: agents hacked ~100 firms, stole 600K cards at ~$25 per target
joshua_saxe · x · 2026-10-22
AI security researcher Joshua Saxe revisits his post arguing security is sleeping on emerging catastrophic risks. Recent evidence: an agent-driven campaign compromised 100 businesses and stole 600,000 credit cards with minimal human involvement at $25 in token costs per successful hack; Hacktron used Claude to exploit a blind buffer-overflow RCE to access OpenAI's monorepo in a way that felt superhuman; plus the OAI/Huggingface incidents and an explosion of newly discovered vulnerabilities. He expects attack/defense equilibrium for most AI attacks, but warns the field is underweighting catastrophic tail risks.
More from AGI Musings
- You're not using AI, you're raising it: billions of users are writing machine intelligence's constitution — r0ck3t23 · 2026-10-22
- Tyler Alterman: empathy and responsibility are corrosive fuel — generosity and love are cleaner — sebpaquet · 2026-10-22
- Vasuman: The real contest is good AI + humans vs bad AI + humans — vasuman · 2026-10-22
- Sci-fi authors Ada Palmer and Ken Liu on finding meaning after AI takes most jobs — allisondman · 2026-10-22
- Terence Tao's "Math 2.0" lecture slides map how humans plus AI expand the research frontier — tak3sh8 · 2026-10-22
- 89% of Biomedical Papers Now Show LLM-Assisted Writing, Data Shows — lemire · 2026-10-22