Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
visarga
11 months ago
|
parent
|
context
|
favorite
| on:
Attention Is Off By One
I interpreted it as cracking a joke about miscalibrated probs in softmax, it tends to be 99.9% sure, or 0.1%, but little in-between.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: