metr.org

Measuring AI Ability to Complete Long Tasks (opens in new tab)

Covered by 12 sources See all sources covering this story including anthropic.com, lesswrong.com

Analysis code is available on Github. Raw data available here

Read the original article
Sign in to keep reading the full article.
Sign UpLog In

Covered in 14 articles

anthropic.com·

When AI Builds Itself

Feeds
lesswrong.com·

Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

Discussed on Hacker News
Feeds
lesswrong.com·

A (Slightly) Mechanistic Theory for Exponentially Increasing AI Time Horizons?

Feeds
View all 14 ›

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