Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Show HN: Auto-train the harness, not the LLM. cross-model, cross-benchmark gains
(
github.com/workofart
)
4 points
by
megadragon9
21 days ago
|
hide
|
past
|
favorite
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
