Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mcbuilder
31 days ago
|
parent
|
context
|
favorite
| on:
DeepSeek-V4-Flash-Vision-Exp
One of the early results from multimodal training is that it kinda works like cross training. Training vision helps with text tasks and visa versa.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
