Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
K0balt
7 days ago
|
parent
|
context
|
favorite
| on:
How Taalas “prints” LLM onto a chip?
Not all applications are chatbots. Many potential uses for LLMs/VLAMs are latency constrained.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
