Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
redox99
11 months ago
|
parent
|
context
|
favorite
| on:
Attention Is Off By One
I guess you could add a sort of gating operation with a learnable parameter that sends the value to -inf if doesn't reach the threshold.
Of course it might have some other serious repercussions.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Of course it might have some other serious repercussions.