Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
DeepSWE: Measuring coding agents on original, long-horizon engineering tasks
(
datacurve.ai
)
2 points
by
sss111
2 days ago
|
past
|
discuss
DeepSWE Measuring frontier coding agents
(
datacurve.ai
)
2 points
by
e2e4
3 days ago
|
past
|
1 comment
DeepSWE: A contamination-free benchmark for long-horizon coding agents
(
datacurve.ai
)
62 points
by
ammar_x
4 days ago
|
past
|
20 comments
DeepSWE Benchmark
(
datacurve.ai
)
5 points
by
xfax
4 days ago
|
past
|
discuss
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
