Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
gamegoblin
on July 6, 2023
|
parent
|
context
|
favorite
| on:
Scaling Transformers to 1B Tokens
Misremembered, the main thrust of the comment still stands, the 100K context window isn't "real", it would be absurdly expensive to do it for real. They are using a lot of approximation tricks to get there.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: