Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fudged71
on Sept 16, 2024
|
parent
|
context
|
favorite
| on:
g1: Using Llama-3.1 70B on Groq to create o1-like ...
It's a chicken and egg situation. You don't know a model's capabilities until it is trained. When you then change the training with that learning, it will have modified capabilities.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: