Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
layer8
12 days ago
|
parent
|
context
|
favorite
| on:
We Will Not Be Divided
Sure, but we could have Hetzners and OVHs who just provide the compute for whatever model we want to run.
help
medi8r
12 days ago
[–]
Checked the DDR5 price lately?
reply
layer8
12 days ago
|
parent
[–]
I didn’t claim that it would be cheap. But I’d rather see the real cost of SOTA LLM use exposed. On the other hand, reportedly SOTA LLM inference is profitable nowadays, so it can’t be that expensive.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: