Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
thomashop
9 months ago
|
parent
|
context
|
favorite
| on:
NotebookLlama: An open source version of NotebookL...
Funnily, even two different LLMs, when put in conversation with each other, can end up completing each other's sentence. I guess it has something to do with the sequence prediction training objective.
newsbinator
9 months ago
[–]
And this regularly happens with humans too
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: