Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
thesehands
4 months ago
|
parent
|
context
|
favorite
| on:
Tau² benchmark: How a prompt rewrite boosted GPT-5...
This is very much what dspy aims to address. Learning the incantations necessary to prompt well can be replaced by an algorithmic loop and example labelled cases.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: