Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
wyre
4 days ago
|
parent
|
context
|
favorite
| on:
Claude Cookbook
Ya, I don't know if there are any human benchmarks or tests for efficiency and results using llms.
help
embedding-shape
4 days ago
[–]
Pit two people with different "prompt engineering" familiarity against each other in real-time, with the same goal, see who builds the best thing, judged by other human experts.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: