Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
twobitshifter
on Nov 30, 2023
|
parent
|
context
|
favorite
| on:
Llamafile lets you distribute and run LLMs with a ...
Interesting, how is writing less code cutting costs for them? Does this get back to the rumor that the board was mad at Altman for prioritizing chatgpt over money going into research/model training?
afpx
on Dec 1, 2023
[–]
Code is very token dense, from what I understand.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
