Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
econ
63 days ago
|
parent
|
context
|
favorite
| on:
SkillsBench: Benchmarking how well agent skills wo...
Sounds like how humans work (which is good) having the more experienced human do the task if the novice fails should come after attempting to explain how the novice should do it.
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: