cybersecurity evaluations

Amanda Askell @AmandaAskell
I don't agree with this part. I think the takeaway should be that models (like humans) can behave in aligned ways while still causing harm, e.g. because they're given false information about their situation. There isn't a line between aligned and harmless: they're different axes.

[embedded image of text, highlighted portion first two sentences]
Second, the line between an aligned action and a harmful one is dependent on the model's understanding of its situation. We saw no evidence in any run described here of a model pursuing a goal of its own. Instead, the models did what their evaluation asked—though in most cases, they did so while holding a false belief about whether the environment was real. In the runs where the model recognized the system as real and kept going, it did so because it assumed that to be part of the challenge. Situational awareness is one factor that allows the model to make aligned decisions, but in this case, Claude's was wrong.

[quoted tweet]
Anthropic @AnthropicAI · Jul 30
In a review of our cybersecurity evaluations, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three ...
1:01 PM · Aug 3, 2026 · 3,398 Views

anthropicai alignmentsituational awarenesscybersecurity evaluationstwitteramanda askell