Security Veterans Mock AI Safety Circles for Rediscovering Decades-Old Attacks

Security veterans are mocking AI safety researchers for presenting classic attacks like side channels, known for 50 years, as novel risks simply by framing them as ASI concerns.

2026-09-19 ~ 2026-09-19 · 2 related posts

• Security veteran mocks AI safety folks for rediscovering 50-year-old threat classes — inductionheads · 2026-09-19
• AI researchers rediscovering 50-year-old side-channel attacks, just add "but it's an ASI" — nptacek · 2026-09-19