Even unhackable stacks won't save you: AI attack pace vs slow software migration
jd_pressman · x · 2026-10-24
In a discussion with MIRI's Anna Salamon, jdpressman argues that formal verification and memory safety don't deliver perfect security—they simply don't catch all software errors.
- AI has accelerated cybersecurity into a 24/7 pace, with attackers acting faster and breach consequences growing accordingly.
- Key point: even if code became free and an unhackable software stack existed tomorrow, many parties wouldn't migrate in a reasonable timeline—and from an AI-vulnerability perspective, "reasonable" might mean days.
The thread extends AI safety concerns beyond alignment to the inertia of legacy software ecosystems as a standing attack surface.
More from AGI Musings
- Top PL researcher Talia Ringer: no time for research, health and daughter all at once — anshulkundaje · 2026-10-24
- David Deutsch: embodiment is basically irrelevant for consciousness — "I am a computer program!" — burny_tech · 2026-10-24
- "Nobody mocked cybersecurity risks — we mocked mass-unemployment doomers" — AlexTensor · 2026-10-24
- Anthropic exec's "we tried to warn the world" draws accusations of AI-lab hypocrisy — AlexTensor · 2026-10-24
- One cartoon nails why enterprise AI transformation stalls: missing data, process, training, change — kuanhoong · 2026-10-24
- microagi promises a billion robots by 2029; skeptics say scene understanding won't be solved by 2027 — AlexTensor · 2026-10-24