Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
whatever1
on Nov 23, 2023
|
parent
|
context
|
favorite
| on:
OpenAI researchers warned board of AI breakthrough...
The thing is that a LLMs can point out a logic error in their reasoning if specifically asked to do so.
So maybe OpenAI just slapped an RL agent on top of the next-token generator.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
So maybe OpenAI just slapped an RL agent on top of the next-token generator.