Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
seunosewa
9 days ago
|
parent
|
context
|
favorite
| on:
AGENTS.md outperforms skills in our agent evals
What if they used the same compressed documentation in the skill? That would be just fine too.
OJFord
9 days ago
[–]
Sure but it would be a trivial comparison then, this is really about context vs tool-calling.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: