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.

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.

Source: TechMeme
Source Link: https://www.techmeme.com/261023/p13#a261023p13