Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
tbalsam
6 months ago
|
parent
|
context
|
favorite
| on:
Measuring AI Ability to Complete Long Tasks
There are versions of this kind of benchmark with a higher threshold, however, it only seems to adjust the timetables by a linear amount, so you're only buying 1-2 years or so depending on what you want that % success rate to be.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: