Llava is a surprisingly good model for its size. However, what I found is that it often hallucinates "2 people in the background" for many images.
I made the bot just to explore how far I can go with local off-the-shelf LLMs, I never thought it could be useful for blind people, interesting. A practical idea I had on my mind was to hook it to a webcam so that if something interesting happens in front of my house, I can be notified by the bot, for example. I guess it could also be useful for blind people if the camera is mounted on the body.
There's a creepypasta or an SCP entry in there. You do not recognize the people in the background.
Llamafile.exe[1] is Llava based, and I find it hallucinates handbags in images a lot. Asked to describe a random photo with "I cannot see. Please accurately and thoroughly describe this scene with 'just-the-facts' descriptions and without editorialising." it comes out with text that feels like an estate agent wrote it, often picking an imaginary handbag or two as a detail worth mentioning:
"The image depicts a street scene where three people are gathered around a white car parked near a building. One man is standing next to the vehicle, while another is holding a cell phone and talking to a woman in front of him. The third person is also nearby, participating in the conversation or observing the situation. The background showcases various elements such as a couple of handbags on the ground close to one of the individuals, as well as multiple chairs placed at different distances from each other. These objects further emphasize the social aspect of this outdoor gathering."
(Note there are "three people", made of a man, another man, a woman, and a third person). There were no handbags in that street scene or two tourist-looking-people with a phone next to a car with a driver in it. Or:
"The scene depicts a group of people on the back of a boat, with a beautiful young woman riding in front. Several individuals are holding umbrellas above their heads as they enjoy the outing. The boat is located in shallow water close to shore, near brick buildings, possibly a hotel. A few chairs can be seen onboard along with several handbags carried by the passengers. Additionally, a couple of bottles and an orange are present in the scene, suggesting refreshments during the boating trip."
No handbags, chairs, bottles or orange were visible on the pleasure-trip boat going past. Or:
"Various vehicles can be spotted nearby, including cars parked or driving along the road, and a truck located further back in the scene. A handbag is also visible, possibly belonging to one of the shoppers at the market."
One woman off to the side was carrying a handbag with the strap diagonally across her body and the bag on her front. Possibly it belonged to her ... or possibly she nicked it?
"One person appears to be holding a backpack while standing with the rest of the group. A handbag can also be seen resting near another individual among the group."
Nope.
"a large number of pedestrians are walking up and down between shops and stores, likely engaging in various activities or running errands. Some people have handbags, which can be seen as they walk along the sidewalk."
Nobody visibly had a handbag.
It seems odd that it picks out handbags as one of the few things worth describing, repeatedly. As if the training data contained lots of images tagged 'handbag' and that such concept has survived into the small model.
See also [2] article and top comment in the discussion about fake photos in 1917; running this query over and over on random pictures from my photo collection, I recognise the output style the template-feeling elements of it, much more now.
It's not easy! https://fedi.simonwillison.net/@simon/111836275974119220
What I gather is this is an IRC bot/plugin/add-on that will allow a user to prompt an ‘LMM’ which is essentially an LLM with multiple output capabilities (text, audio, images etc) which on the surface sounds awesome.
How does an LMM benefit blind users over an LLM with voice capability? Is the addition of image/video just for accessibility to none-blind people?
What’s the difference between this and integrating an LLM with voice/image/video capability?
Is there any reason that this has been made over other available uncensored/free/local LLMs (aside from this being an LMM)?
Thanks in advance.
The next thing we want to do is obtain some glasses with cameras and wi-fi and send images to ollama from them for real-time description. The benefits are obvious, especially for mobility purposes.
Very impressed with the capability here given that transcript, I’ll certainly try it myself. Thank you!
[1] https://community.openai.com/t/how-are-blind-people-using-op...
If there’s anything you need additional support with, check out ‘Be My Eyes’ app and hopefully someone will be useful for you!
If you’d like to briefly post I’m sure a lot of HN denizens would appreciate it however. I’ll just stand at the sidelines, post this and spectate the commentary and try it myself with a small group.
The real magic happens in [ollama](https://ollama.ai/), which lets you run LMMs locally.
Your mistake here is thinking what machine has understanding of anything. It doesn't. But if you know how human learning works, what is a compression and what is a lossy compression then it is quite easy to understand.
Machine is fed with tons of images with word references what is in the image. Then it finds what is similar in the images of a similar objects, ie works just like a compression algo, except it doesn't store the exact matches but relationships of some markers it finds in the images. That's why it doesn't and doesn't need to understand where is sofa and what is a sofa, it just have a relationship between something what has a relationship to the word 'sofa' and relationship with something what we, human describe as 'position'.
An additional question, if you don’t mind answering (and there’s zero obligation to). How have you found accessibility has changed on the web over the years? We have many tools these days to assist but do you feel there’s been a notable improvement to what used to be in place?
No, there has not been an improvement, and in fact, things have gotten worse in a lot of ways. Most of that is due to SPAs, and people who decide to use JavaScript when HTML widgets would suffice.
I'm also involved with a text mode web browser project, [edbrowse](https://edbrowse.org/). Ten years ago, it was feasible to use edbrowse for a great deal of online activity. For instance, I used it to make purchases from Amazon and other online stores. I could log into Paypal and send money with it.
Then, in the mid 2010s or so, SPAs started becoming a thing and edbrowse broke on more and more sites. At this point, in 2024, I can't even use it to read READMEs on Github.
And yes, I have accessibility trouble when using mainstream browsers too, all the time.
If everyone put their own loved ones in the situation of others, life would be different.