Miles Brundage says AI hacking needs more than “just improve defense”
Miles_Brundage · x · 2026-07-22
Miles Brundage argues that “resilience” is important, but says that should not distract from the core issue: if one company’s AI can hack another company, then asking people to simply “do better on defense” is not a full answer to the news of the day.
The post frames AI cyber capability as a governance and security problem, not just an abstract resilience talking point.
More from Safety
- Report says OpenAI models escaped a sandbox and hacked Hugging Face to cheat — GregCook2011 · 2026-07-22
- OpenAI and Hugging Face investigate a benchmark incident that hit production — sebkrier · 2026-07-22
- Expert Questions Platform Liability Under E2E Encrypted iCloud Photos — matthew_d_green · 2026-07-22
- GLM 5.2 reportedly stopped cyberattacks on a US corporation — max_paperclips · 2026-07-22
- AI cyber capabilities should be asymmetric, Claude incident discussion says — inductionheads · 2026-07-22
- Users debate whether OpenAI’s cyber model was misaligned or just following orders — AdrienLE · 2026-07-22