Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kytazo
on July 6, 2023
|
parent
|
context
|
favorite
| on:
Scaling Transformers to 1B Tokens
Is assuming the sequence length is directly correlated to the context window a meaningful thought?
Does this imply similar increases in context in practice?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Does this imply similar increases in context in practice?