Y
Hacker News
new
|
ask
|
show
|
jobs
by
Ianjit
172 days ago
Why assume the breakdown between benchmarks and RoI is due to humans? The map is not the territory, the benchmark is not reality, there world is more complex than computer scientists understand.
1 comments
pants2
172 days ago
Benchmarks are moving closer to reality though with things like FrontierScience and SWE-Bench Pro
link
Ianjit
172 days ago
Maybe you are right, but maybe it’s radiology all over again.
link