HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
anukin
60 days ago
|
parent
|
context
|
favorite
| on:
OpenAI Jalapeño: Better than Nvidia Blackwell
I would assume asic based llm would work really well. Why did it not go well?
striking
60 days ago
[–]
https://chatjimmy.ai/
runs Llama 3.1-8B on an ASIC as a demo by
https://taalas.com/
I believe.
That's quite a few parameters shy of today's trillion-weight behemoths, but it is fast.
mchusma
60 days ago
|
parent
[–]
You are correct. I think this is the bull case. It seems like this would be useful right now for some things (eg moderation).
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search:
