The coverage then said only a diff against the original model catches it. The paper's own scan, with no original, flagged 91.4% of edited models.
“Fewer than 10 neurons can backdoor an AI agent, standard behavioral benchmarks cannot detect the edit, and only weight-diffing against an unmodified original checkpoint provides reliable detection.”
AI Weekly summary of Microsoft Research's Lazarus work, echoed by The Next Web, 11 November 2026
Recorded 13 November 2026. Our ruling means: literally true, materially misleading.
Their agent-built detection methods flagged 91.4% of held-out modified checkpoints, with a 9.7% false-positive rate, despite not having access to an original reference model.
First membership: 30 days free, then A$89 a year. One introductory trial per customer. Card required; renews annually until cancelled. Cancel before the trial ends to avoid the first charge.
Free · one story a night
Don't take the AI industry's word for it.
“Anthropic has met the AI research and development capability threshold in its Responsible Scaling Policy.”
TRUE, BUTHeadline Over FilingAnthropic, in its IPO prospectus
That's the latest lead check. One a day, receipts attached, in your inbox before someone repeats it at you. Free.
No spam. Unsubscribe in one click. Receipts or it didn't happen.
Pranjal Gupta writes every check himself. Former enterprise architect, from the implementation side. Not a team of anonymous raters.
