Read

Read

1059 bookmarks
Custom sorting
The Decline of Deviance
The Decline of Deviance
I think I'm weird, but still bounded weird. I suspect it's more that weird is at the edges, in marginalized communities that this writer isn't a part of?
·experimental-history.com·
The Decline of Deviance
Disrupting the first reported AI-orchestrated cyber espionage campaign \ Anthropic
Disrupting the first reported AI-orchestrated cyber espionage campaign \ Anthropic
Couple or 🤔 brags in here that ignore the fact that their agent was at fault here.
They did so by jailbreaking it, effectively tricking it to bypass its guardrails. They broke down their attacks into small, seemingly innocent tasks that Claude would execute without being provided the full context of their malicious purpose.
This raises an important question: if AI models can be misused for cyberattacks at this scale, why continue to develop and release them? The answer is that the very abilities that allow Claude to be used in these attacks also make it crucial for cyber defense.
·anthropic.com·
Disrupting the first reported AI-orchestrated cyber espionage campaign \ Anthropic