"We're investigating a report claiming unauthorized access to Claude Mythos Previous through one of our third-party vendor environments."
"The new Mythos model has gained notoriety of late for its supposed ability to sniff out security flaws in operating systems and internet browsers."
"Several unauthorized users reportedly gained access to Mythos through a developer portal and by making an educated guess as to where the model might be located."
"Anthropic was recently designated as a supply chain risk by the US Department of Defense, but has been in talks with the Trump administration of late to have that label removed."
Anthropic is looking into unauthorized access to its Claude Mythos model, which was accessed through a third-party contractor portal. The group involved is reportedly not using the model maliciously. The Claude Mythos Preview was released as part of Project Glasswing and is limited to trusted companies. Unauthorized users gained access through educated guessing and may have access to other unreleased models. The Mythos model is noted for identifying security flaws, raising concerns about potential AI-generated cyber attacks.
Read at Engadget
Unable to calculate read time
Collection
[
|
...
]