Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
RagnarD
3 days ago
|
parent
|
context
|
favorite
| on:
A CPU that runs entirely on GPU
You're both completely missing the point. It's important that an LLM be able to perform exact arithmetic reliably
without
a tool call. Of course the underlying hardware does so extremely rapidly, that's not the point.
help
jdjdndnzn
3 days ago
|
next
[–]
The computer ALREADY does do math reliably. You are missing the point.
reply
kruffalon
2 days ago
|
prev
[–]
Could you explain why that is?
reply
koolala
2 days ago
|
parent
[–]
A tool call is like 100,000,000x slower isnt it?
reply
kruffalon
2 days ago
|
root
|
parent
[–]
No idea really, but if it is speed related I would have thought that OP would have used
faster
rather than
importance
to try and make their point.
reply
koolala
2 days ago
|
root
|
parent
[–]
It's both. Being dirrctly a part of it makes it integrated into its intelligence for training and operation.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
