Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ra
on Nov 23, 2023
|
parent
|
context
|
favorite
| on:
OpenAI researchers warned board of AI breakthrough...
Indeed. LLM is an application on a transformer trained with backpropagation. What stops you from adding a logic/mathematic "application" on the same transformer?
seanhunter
on Nov 23, 2023
[–]
Nothing, and there are methods which allow these types of models to learn to use special purpose tools of this kind[1].
[1]
https://arxiv.org/abs/2302.04761
Toolformer: Language Models Can Teach Themselves to Use Tools
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: