Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Why SWE-bench Verified no longer measures frontier coding capabilities
(
openai.com
)
10 points
by
tedsanders
12 days ago
|
hide
|
past
|
favorite
|
discuss
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
