Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
MacsHeadroom
on April 4, 2023
|
parent
|
context
|
favorite
| on:
Show HN: Promptr, let GPT operate on your codebase...
I think GPT4All's inferior quality dataset would make a worse combined model than strict Vicuna. Vicuna-30B will likely be better than GPT-3.5 level and approaching GPT-4 level when it's done training, but run slow on CPU.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
