Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
moonchrome
on Aug 26, 2023
|
parent
|
context
|
favorite
| on:
Beating GPT-4 on HumanEval with a fine-tuned CodeL...
I'm guessing the problem is that you're constrained by memory bandwidth and not computation power and this is inherent to the algorithm, not an artifact of any one implementation.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
