Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
flakiness
19 days ago
|
parent
|
context
|
favorite
| on:
Claude Opus 4.5
They should've used an error rate instead of the pass rate. Then it'll get the same visual appeal without cheating.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: