Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
vanviegen
on Sept 12, 2024
|
parent
|
context
|
favorite
| on:
Learning to Reason with LLMs
It doesn't do the 'thinking' in English (inference is just math), but it does now verbalize intermediate thoughts in English (or whatever the input language is, presumably), just like humans tend to do.
konschubert
on Sept 13, 2024
[–]
Agreed. It we never "just autocomplete" unless your definition of "autocomplete" includes "look at the whole body of text".
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: