Frontier AI Companies Have Meh Cybersecurity as Internal Agents Pose Risks
RyanGreenblatt · x · 2026-07-24
AI safety researcher Ryan Greenblatt points out that frontier AI companies have mediocre computer security.
This is alarming considering they possess highly capable (and potentially misaligned) AI systems for cyber offense and plan to develop even wilder models in the coming years, leading to severe security risks.
Related event: AI Cyberattack and Control Risks: Debating Defense and Safety(9 posts)→
More from Safety
- Production AI agent scored 95% robustness at baseline, 37% under adversarial attack — njyx · 2026-10-27
- Anthropic IPO filing reveals 5-7% of revenue came from rule-breaking customers, at least $814M — henkvaness · 2026-10-27
- Blanket AI restrictions on reverse engineering punish defenders, not attackers — mark_k · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Dev warns abliterated models could wreck software supply chains with 1000+ transitive dependencies — nitarshan · 2026-10-27
- JPMorgan's Dimon says Anthropic's Mythos raised the bank's cyber risk tenfold — ChuckDBrooks · 2026-10-27