Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
og_kalu
14 hours ago
|
parent
|
context
|
favorite
| on:
How we used GPT-4o for image detection with 350 si...
>visual llm works on textual descriptions
SOTA V-LLMs do not work on textual descriptions.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
SOTA V-LLMs do not work on textual descriptions.