On the agent data question there is now measured incident data sitting alongside the lab results. Anthropic's threat intelligence report of 10 September 2026 describes a compromise in which operators reached roughly 200 downstream customer organisations through a single software vendor, then pulled over 2,100 Azure AD token sets spanning more than 40 corporate tenants in about 34 hours, with AI agents doing nearly all of the work. The poisoning papers describe the input side. That case shows the throughput at the other end. The report does not say how much of those 34 hours ran unattended.
These are so good! Any chance you might do weekly ones in the future?
Thanks Dhruv. I dream of being able to lock myself away and read papers all day - let's see!
On the agent data question there is now measured incident data sitting alongside the lab results. Anthropic's threat intelligence report of 10 September 2026 describes a compromise in which operators reached roughly 200 downstream customer organisations through a single software vendor, then pulled over 2,100 Azure AD token sets spanning more than 40 corporate tenants in about 34 hours, with AI agents doing nearly all of the work. The poisoning papers describe the input side. That case shows the throughput at the other end. The report does not say how much of those 34 hours ran unattended.