Y
Hacker News
new
|
ask
|
show
|
jobs
Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering
(
arxiv.org
)
1 points
by
popey
44 days ago
1 comments
pqtr2
44 days ago
Couldn't agree more. Coding benchmarks are just a score. Benchmark the harness.
link