Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
syllogism
on Sept 13, 2023
|
parent
|
context
|
favorite
| on:
Against LLM Maximalism
Nothing's to stop us, and in fact we can do that now! This is basically what the post advocates for: replacing the LLM calls for task-specific things with smaller models. They just don't need to be LLMs.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: