Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
New method for testing AI using real work-flows
(
github.com/assimilatedhuman
)
2 points
by
ballista2026
4 days ago
|
past
|
discuss
LLM INQUISITOR: Evaluating how AI models handle long, realistic tasks
(
github.com/assimilatedhuman
)
1 point
by
ballista2026
11 days ago
|
past
|
discuss
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
