Back to article
METR

Many SWE-bench-Passing PRs Would Not Be Merged into Main (opens in new tab)

Covered by 5 sources See all sources covering this story including latent.space, CognitionDiscussed on Hacker News

Covered in 5 articles

latent.space
·

[AINews] FrontierCode: Benchmarking for Code Quality over Slop

Feeds
Cognition·

Introducing FrontierCode

Discussed on Hacker News
Feeds
cognition.com·

Frontier Code (AI coding benchmark)

Discussed on Hacker News
Feeds
beyondtheprior.com·

Why LLMs (still) lack taste

Discussed on Hacker News
Feeds
Vincent Schmalbach·

The AI Coding Era Makes Boring Tests More Valuable

Discussed on Hacker News
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