Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
phillipcarter
on May 1, 2024
|
parent
|
context
|
favorite
| on:
Run llama3 locally with 1M token context
This has been my experience across all of them, yes. Especially when I ask it to select a decently-sized subset of the text I pass in, as opposed to just doing a needle-in-the-haystack type thing.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: