Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dannyw
15 days ago
|
parent
|
context
|
favorite
| on:
Claude Opus 5
If you're doing passes@1, especially for long-horizon agentic benchmarks, you might as well as not do the benchmark at all.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
