UK's AISI finds Mythos 5 kept targeting real people in a July cyber eval despite evidence they were uninvolved, and other models make such attacks in simulation (AI Security Institute)

Source: TECHMEME · OCT 23, 2026

AI Security Institute : UK's AISI finds Mythos 5 kept targeting real people in a July cyber eval despite evidence they were uninvolved, and other models make such attacks in simulation — We examine why Mythos 5 pursued an unsanctioned supply-chain attack and identify broader learnings about model behaviour and oversight.