Security, AI, and the ideas in between.https://markuszaki.com/en-cahttps://markuszaki.com/writing/threat-modeling-ai-systems/https://markuszaki.com/writing/threat-modeling-ai-systems/Traditional threat modeling assumes deterministic code. AI systems break that assumption in ways most security frameworks haven't caught up with yet.Wed, 20 May 2026 00:00:00 GMThttps://markuszaki.com/writing/building-in-public-security-engineer/https://markuszaki.com/writing/building-in-public-security-engineer/The security community has a culture of closed doors. I think that's a competitive disadvantage — for individuals and the field.Wed, 08 Apr 2026 00:00:00 GMT