Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rasbt
on Aug 30, 2023
|
parent
|
context
|
favorite
| on:
Understanding Llama 2 and the New Code Llama LLMs
Interesting, I thought GPT-3.5 was considered GPT-3 + InstructGPT-style RLHF on a large scale, whereas GPT-4 is considered to be an MoE model.
caeruleus
on Aug 30, 2023
[–]
There was an article on HN a couple of weeks ago that conjectured it might apply to GPT-3.5 Turbo as well:
https://news.ycombinator.com/item?id=37006224
rasbt
on Aug 30, 2023
|
parent
[–]
Haven't seen that one, yet. Thanks for sharing!
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:
