LLaVaVision
AI
vision language model app
SHOW HN2023
How HN took it
1 positive, 5 neutral or asking, 2 mixed, 2 critical, out of 10 comments about the project. Thread score -0.04.
Performance: 0 for, 2 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Cool, useful idea for accessibility
From 3 comments
Wait an actual cool peace tech on the HN front page? What happened here 0_0 Cool peace of tech!! keep on doing great work.
anon23432343 on HNThis is cool! One thing that can be easily improved is that the narrator is still trying to describe everything, while people using Be My Eyes they usually got specific purposes…
enoch2090 on HNawesome, love the idea and maybe putting a default prompt like: "this images comes from the persons POV that ask you questions" instead of "a person holding something" "you are…
umtksa on HN
Interest in whisper.cpp and task-specific prompts
From 1 comment
This is cool! One thing that can be easily improved is that the narrator is still trying to describe everything, while people using Be My Eyes they usually got specific purposes…
enoch2090 on HN
Objections
Narrator describes everything rather than focusing on user's purpose
From 1 comment
This is cool! One thing that can be easily improved is that the narrator is still trying to describe everything, while people using Be My Eyes they usually got specific purposes…
enoch2090 on HN
Model hallucinates as descriptions go on
From 1 comment
I noticed that it "hallucinates" in the most direct sense of the word as the description goes on.
lxe on HN
Name borrows from Be My Eyes
From 1 comment
A "Be My Eyes web app"? Well whatever. I guess Be My Eyes is just gonna be known for its Be My AI anyway. As soon as Llava is able to read text, this is gonna be pretty nice. I…
devinprater on HN
Requests
Add text reading once LLaVA can read text
From 1 comment
A "Be My Eyes web app"? Well whatever. I guess Be My Eyes is just gonna be known for its Be My AI anyway. As soon as Llava is able to read text, this is gonna be pretty nice. I…
devinprater on HN
Support query inputs and refined prompts
From 2 comments
This is cool! One thing that can be easily improved is that the narrator is still trying to describe everything, while people using Be My Eyes they usually got specific purposes…
enoch2090 on HNawesome, love the idea and maybe putting a default prompt like: "this images comes from the persons POV that ask you questions" instead of "a person holding something" "you are…
umtksa on HN
Use for video games and inaccessible apps
From 1 comment
A "Be My Eyes web app"? Well whatever. I guess Be My Eyes is just gonna be known for its Be My AI anyway. As soon as Llava is able to read text, this is gonna be pretty nice. I…
devinprater on HN
Questions
How does model accuracy compare to GPT-4 Vision?
From 1 comment
Do you know how the model accuracy compares to GPT-4 vision?
FrenchDevRemote on HN
Can it identify exact brands and models?
From 1 comment
Is there any solution that just identifies the object as accurate as possible? For instance when it sees a t-shirt, can be identify the exact brand and model?
ReD_CoDE on HN
Alternatives named
GPT-4 Vision / ChatGPT
From 2 comments
Yes, GPT Vision / ChatGPT is very accurate. CogVLM is also very powerful as a self-hosted solution.
lxe on HNDo you know how the model accuracy compares to GPT-4 vision?
FrenchDevRemote on HN
CogVLM
From 1 comment
Yes, GPT Vision / ChatGPT is very accurate. CogVLM is also very powerful as a self-hosted solution.
lxe on HN
Be My Eyes / Be My AI
From 1 comment
A "Be My Eyes web app"? Well whatever. I guess Be My Eyes is just gonna be known for its Be My AI anyway. As soon as Llava is able to read text, this is gonna be pretty nice. I…
devinprater on HN