Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
atq2119
on May 5, 2023
|
parent
|
context
|
favorite
| on:
Google “We have no moat, and neither does OpenAI”
It should work. After the initial prompt processing, token generation is typically limited by memory bandwidth more than by compute.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
