Concerns grow over Mythos AI

AnthropicÕs new Mythos AI model is raising concerns after the
company said the preview had found thousands of serious
vulnerabilities in every major operating system and web browser

MYTHOS DEBUT

Apr 7, 2026: Launch of Claude
Mythos Preview Ð AI tool designed
for defensive cybersecurity tasks

Model rolled out through initiative
called ÒProject GlasswingÓ

Access granted to tech majors Ð
including Amazon, Microsoft, Nvidia
and Apple

Access also extended to group of
more than 40 other organisations
that build or maintain critical software
infrastructure

CONCERNS

Experts warn model
can identify and exploit
previously unknown
vulnerabilities faster
than companies can
repair them

Advanced coding
and autonomous
capabilities could speed
up sophisticated
cyberattacks,
particularly in sectors
such as banking

During debut, Anthropic said
modelÕs ability to find software
flaws could, if misused, pose serious
risks to economies, public safety
and national security

White House
and Anthropic CEO
Dario Amodei
(right) discussed
working together
amid fears over
Mythos

U.S. government planning to
make version of Mythos available
to major federal agencies

Model raised alarm bells in UK,
with authorities holding talks with
banks and cybersecurity officials
to assess possible risks

Source: Reuters
Pictures: Getty Images
© GRAPHIC NEWS