Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
user3939382
8 days ago
|
parent
|
context
|
favorite
| on:
AGENTS.md outperforms skills in our agent evals
I’m working on an AGI model that will make the discussion of skills look silly. Skills strikes in the right direction in some sense but it’s an extremely weak 1% echo of what’s actually needed to solve this problem.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: