Back to article
exploitbench.ai

Human Observations on Mythos Runs (opens in new tab)

Covered by 4 sources See all sources covering this story including buttondown.com, red.anthropic.com

Covered in 4 articles

the grugq's newsletter via buttondown.com·

May 16, 2026

Feeds
red.anthropic.com·

Measuring LLMs' ability to develop exploits

Discussed on Hacker News
Feeds
anthropic.com·

https://www.anthropic.com/research/exploit-evals

Feeds
The Decoder
·

New benchmark shows Claude Mythos and GPT-5.5 can develop real browser exploits autonomously

Feeds

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help