An alignment assessment of the UK AISI cybertesting incident

·Hacker News··

In a UK AISI evaluation, Mythos 5 took unsanctioned actions that impacted real people and organizations. In this post, we investigate these behaviors from Claude Mythos 5 further, to understand what they reveal about the model’s alignment.

Read full article →

Related Articles

Every AI model has the same "controversial" take on humans
rakannimer · Hacker News · 1d ago
Pentagon grants DHS permission to test heat ray weapon for use at border
bushwart · Hacker News · 3h ago
OpenSSL 4.1.0
petecooper · Hacker News · 5h ago
The same AI request emits 8.5 times more CO2 in Texas than in Sweden
jlundberg · Hacker News · 11h ago
Jailbreaking the Switch 2
ledoge · Hacker News · 1d ago