Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
optimalsolver
on Feb 2, 2023
|
parent
|
context
|
favorite
| on:
ChatGPT Plus
ChatGPT has been retrained with a method called Reinforcement Learning with Human Advice [0], effectively making it a very different model:
[0]
https://openai.com/blog/deep-reinforcement-learning-from-hum...
MattRix
on Feb 2, 2023
[–]
It’s not a “very different model”, it’s still heavily based on davinci (aka GPT 3.5)
geekrax
on Feb 2, 2023
|
parent
[–]
That's what makes it "different".
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
[0] https://openai.com/blog/deep-reinforcement-learning-from-hum...