Y
Hacker News
new
|
ask
|
show
|
jobs
by
ben_w
2 hours ago
What's "exponential" about AI development?
The METR task-completion time horizons, for one.
https://metr.org/time-horizons/
1 comments
zozbot234
15 minutes ago
Lousy benchmark, they explicitly focus on the easiest tasks to automate for AI (i.e. heavily cherry picked outcomes) and it seems that they don't bother to test anything except just-released proprietary models.
link