Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
og_kalu
10 months ago
|
parent
|
context
|
favorite
| on:
g1: Using Llama-3.1 70B on Groq to create o1-like ...
Internally, LLMs know a whole lot more about the truth and uncertainty of their prediction than the say. Pushing that to words is difficult but not impossible.
https://news.ycombinator.com/item?id=41504226
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:
https://news.ycombinator.com/item?id=41504226