Be My Eyes and privacy: can you opt out of model training?

Hi,
If you live in the EU or the UK, you can ask them to delete your images if you don't want them stored. That's because of the data protection laws here. I don't know what happens if you live outside these juristictions. I don't think you can get all your images automatically deleted from the server every time you take a picture. Recently I asked them to delete a picture, but they actually ended up deleting my whole image history with them which was fine. It took them a few days to get back to me.

I would love to use AI for describing certain things, like artist made images, and do not do this most of the time because the of the way OpenAI indescriminately uses and scrapes for data, because i know many artists do not want their work contributing namelessly to the model's success. Having an option not tod o this in any AI solutions would be a huge sstep forward.

The OpenAI Ts&Cs are clear that data uploaded via their business tools including the API is not used for training. Since Be My Eyes is using the ChatGPT models via the API I would therefore expect data sent to it to be covered by these terms.

It could be the case that they just wish to reserve the right to let the third-party AI tool store and process the images and data sent, while it might still be true that GPT/OpenAI does not do that for the time being. Be My Eyes might even switch to some other AI model or offer multiple options sometime in the future.

You mean that the pictures I ask be my eyes are not deleted after I got a description but they are some where else?

hey,
am so glad you emailed. live in a place where data protection laws aren't that good. and wouldn't want my images to be stored. i would also love to have the option to opt out. since open AI and things like chatgpt are being used. till then, ig i'll use it a little less. i use it less but friends who regularly need help use it a lot more so maybe we'll just avoid using it for personal or sensitive images till then.

that's what.
this is just vague. and more vague for those of us who don't live at places having good data protection laws.
don't know what the storage period is.

If you would like to bypass be my eyes and skip directly to open AI, there is a shortcut somewhere, I believe it’s on the main page right now, this will allow you to jump directly to using the API, though it will cost you.

thanks so much

Be My AI was amazing when it was the only way to access GPT-4 Vision, but now that it's publicly available for all to use, having a direct connection with the AI provider is better not only for privacy reasons but because you can generally get better responses out of it, since you can better teach it your needs and expectations.

Tools like VOCR, AI Content Describer for NVDA on Windows, or my shortcuts are great ways to access these AI models directly without needing to know how to code. The hardest thing about the process is setting up a billing agreement with OpenAI but even that is really easy. You sign into your account (you can sign in with Google If you don't want to make an account directly,) drop $5 into the account and you're basically set for a couple months, probably longer now that we have GPT-4O.

OpenAI doesn't train on images you send to them through the API, which is what you're doing when you use one of these tools. There is no middleman here, either. The image goes straight from you directly to OpenAI.

Don't get me wrong, I think Be My AI is amazing, especially because it's free, but if you can spare $5 every now and then, I think you'll be much happier using one of these other tools, even if it's only for a few images here and there.

Do the 2 AI in JAWS picture smart send the photo to be check? Both do a great job and now that you can ask question is great.

I hope the company takes these concerns seriously. Else I am not using Be My AI for descriptions.

I have one and only one simple, short, clear, straightforward question: How on earth am I supposed to know what is featured in an image in which I have no clues as to what is shown and would like to have described by Be My AI or whatever app/AI model? Is this already not exactly why I want and need a description of the image? Uh, okay, I know I asked two questions and neither were short or straightforward. By the way, it is also for the very same reason that we should not be held liable for sharing personal data when uploading images to get their descriptions. It is already after we get those descriptions that we find out what the uploaded photos contain. Besides, would it not be a violation of our privacy to have to ask someone sighted to describe what (s)he sees in a photo? In conclusion, the issue will most likely remain unresolved unless or until we all have access to accurate and quick on-device descriptions without having to upload the images to any remote servers.

I don't like the sound of their response at all.

This is really concerning because we know OpenAI isn't doing this.

OpenAI Enterprise Policy says:

Trust and privacy are at the core of our mission at OpenAI. We’re committed to privacy and security for ChatGPT Team, ChatGPT Enterprise, and our API Platform. We do not train on your business data (data from ChatGPT Team, ChatGPT Enterprise, or our API Platform) You own your inputs and outputs (where allowed by law)

If the AI platform providing the service isn't doing anything with our images, why on earth does Be My Eyes feel like they have to?

this is very concerning.
that's why am pretty sceptical about AI coming more and more into the market. esp in places where we still don't have clear and good IT laws.

Would not be surprise if the data is not sold to others for ads.

They might not train a model themselves, but they could transfer images to other research organizations for RnD.

I have no idea what they mean by to develop products and services that may assist other members of the general public.

Here are some direct quotes below:

We record and store video streams and other images (i) to enforce our Terms of Service, (ii) to promote and preserve safety, and (iii) to improve our Services and create new Services.

We may provide recorded video streams or images to other organizations that are performing research or working to develop products and services that may assist blind and low-vision people or other members of the general public.

If you use Be My AI, the images you submit will be processed by our third party artificial intelligence provider.

If your video or image contains personal information - for example you say your name on the video or show mail with your home address - that information will be included in videos or images that we store and use as described above.

this is yikes

I really don’t care. You probably have more sensitive information about you on social media platforms and internet than Be My Eyes. Not to mention that you are using smart phones and if someone really wants then they can have access to all of your smart phone data, files, pictures etc. Deleting things won’t help either because they are only deleted for ourselves but they are not really gone.

The thing is, when a company accesses, collects, stores, processes, shares and/or sells our personal information, it can base that on its vague privacy policy and practices and assert that it is us who consented to that, making it easier to justify its policies and more difficult for us to object to them; whereas someone doing those things without our express consent will likely face more legal issues and sanctions, and we will at least be able to claim that we never consented to any of their unlawful acts.
There's one phrase that makes me so concerned and annoyed: "including but not limited to". I encounter it in most such agreements where they desperately look for ways to make things as ambiguous and open to interpretation as possible.

For anyone who subscribe to livingblindfully can you send an email to him about this question? He suppose to have good relationship with those people in charge of Be my eyes. This way this question is answer one way or another. I am not a subscriber to it.

How are photos and chat interactions processed and stored, and who will have access to my data?

Be My Eyes initially processes your photos and chats to (a) send them to OpenAI for further processing, (b) provide Be My AI’s descriptions, and (c) give you follow up options. OpenAI processes the photos and chats to provide the AI response.

During our beta testing, Be My Eyes stores all photos and chat interactions on encrypted servers so that we can review them, if necessary, based on tester feedback. That helps us build a better service based on your feedback. It also allows us to address any safety or content issues that may come up. OpenAI does not store the photos or chats after processing them. None of your photos or chats are being used to train the AI.

The storage and use of your photos and chats by Be My Eyes are governed by our privacy policy.

So I don’t see any problems there and the calls with volunteers are recorded anyway for the safety reasons.

Can I have it! Needed so my cat can not send messages to my brain or trying to control me.

Be My AI is not in beta anymore. Even the beta button next to the Be My AI button is removed and everyone can access this feature even new users so it is not in beta anymore.

Hi all,
While I do agree that people should be able to choose whether they want their images used for training purposes or not, there's a take here I don't really agree with. Enes you say, 'we should not be held liable for sharing personal data when uploading images to get their descriptions. It is already after we get those descriptions that we find out what the uploaded photos contain.'. I would say it depends on what you already know about your surroundings. When I take a picture of food packaging or something I want identified, I take said picture in an area where I know I haven't got any paper documents lying about with identifying details on them. Unless you're trying to identify documents, take a selfie or a picture of someone else, what could you possibly be taking a picture of where you wouldn't know whether it could potentially hold identifyable information or not? The only exceptionns to this rule are if you're living with other people and they could have left personal stuff lying about you don't know about, or you're out in public and you want to take a picture of something. In these two scenarios, you should absolutely be aware that personal stuff might get picked up, and if you take a picture outside, random people might end up in the background who wouldn't want to be there. Everybody knows this, right? So to an extent, we should be held liable. We know our surroundings, and we know that when we receive paper documents through the post, they'll contain personal details. It's always recommended by Be My Eyes not to knowingly take pictures of personal documents anyway. If you're really not sure what something is, use Seeing AI. But I definitely think people should have the option to choose whether they want their images stored for training purposes or not. I can opt out of using my images for training purposes in the ChatGPT app. I don't usually care what images Be My Eyes stores apart from one time I took a photo with personal details. I knew this before taking it, but I needed a good description. I knew I could email them and get it deleted anyway.

Hi Tara
You have really good points and I agree with you.
About public places, random people can appear everywhere. For example, sighted people are posting stuff on internet anyway that have random people in the background. It is not uncommon. Plus if you do have people in the background then they usually are not in full view. Also, many public places have cameras so I think that we all have appeared somewhere whether we want it or not.
It is basically the same like we all know that our houses and gardens are seen on Google maps and after a certain time the governments are taking new pictures about the landscapes and updating them on Google maps. Well, maybe someone doesn’t want that everyone can see their family’s car, their house and things in their garden but it is a reality and not for us to decide.
My point is just that we are not snowflakes who are living in a cotton. Unfortunately, this world is not as private as we would like it to be and it won’t never happen.

Well, Seeing AI seems different. Its AI doesn’t have so wide knowledge as Be My AI. Seeing AI is good for documents and short text. Also, I quite don’t believe that Seeing AI won’t store the information because you have a feedback button there where you can react if you liked or disliked the description. Why is it there then? Also, we can’t forget that in Be My Eyes it was the blind community who requested the link sharing of the images and descriptions. I really like the sharing option but in Seeing AI you can’t share anything unless you save the pictures and texts separately.

Yes, Be My Eyes did delete my images after I emailed them and asked them. I asked for one particular image to be deleted. I gave them the day and the approximate timeframe I took the image. They deleted all the images in my account though. My account wasn't deleted. I'm still using the account I've been using for the last few years no problems. It's surprising they're telling you something different actually. I don't see why they'd need to delete your entire account so your images can be deleted. That certainly didn't happen for me. My account is still active and working fine.

I took a random picture then asked it what be my eyes does with the photos and got
Me: What does this service do with the photos i take? Are they stored anywhere?
Be my ai: The photos you take are used to provide you with descriptions and assistance. They are not stored permanently and are only used for the duration of the session to help answer your questions. If you have any concerns about privacy or data handling, you might want to press the "Call a volunteer" button for more detailed guidance.
Me: Are they stored on my account or on be my eyes anywhere?
Be my ai: The photos you take are used temporarily to provide assistance and are not stored permanently on your account or within the Be My Eyes service. They are deleted after the session ends. If you have specific concerns about data storage and privacy, I recommend pressing the "Call a volunteer" button for more detailed information and reassurance.
So thats some positive information.

I hate to break it to you, but if that's not in the terms of service in the Be My Eyes app itself, it is not accurate. AI is prone to making things up and you cannot rely on it for legal things like this or to tell you the truth about something like a terms of service agreement. What it says in the Be My Eyes TOS is what they will be doing with your data, not what the AI says at this moment.

Honestly stuff like this makes me much less likely to use a product at all. This kind of behavior, especially being dircted at a more vulnerable group, feels like we're being preyed upon and taken advantage of. I still have Be My Eyes for when I need to call a volunteer but I will not touch their AI feature with a ten foot pole after reading that we have no option to opt out of having what may be very sensitive information about us on a database (like prescription labels or documents we may not know are visible in a pic). If I could afford Aira I would ditch Be My Eyes completely for being so shady about what they're doing with our information and not giving us, the people who are the whole reason Be My Eyes exists at all, just a group to harvest data from for no good reason they will say.

As far as I can tell, right now companies are doing it because AI has been really hyped up and they're trying to ride a possible wave. But also there are no firm laws or regulations stopping them from doing things that are honestly very morally awful, like literally stealing personal private information from the blind that may put those customers at risk. When companies aren't stopped from doing things that are harmful they will keep doing them whether they can see a direct benefit at the time or not, history has proved that repeatedly. Hopefully the law will catch up sooner rather than later on stuff like this and there is every sign that the AI bubble is about to pop, though how much damage it will do when it does remains to be seen. For now, if something doesn't feel right to you, opt out of that service and don't be afraid to tell the companies why if they ask.

If you wouldn't ask a stranger on the street to read your mail to you, don't ask Be My AI to do it. At least with your neighbor that person won't remember every detail and potentially sell it to a data broker company.

My concern would be why do they need to save them? If we wanted to be save that would be different, if the app pops with a message do you want to save the data? yes or no.

The reply I got also stated that they wouldn't use my data for model training and that I could request my conversation history to be deleted. When I asked why I had to contact them instead of just being able to do that myself within the app, I was told that they did plan on adding such an option.

https://www.bemyeyes.com/blog/be-my-eyes-launches-initiative-to-make-ai-models-more-inclusive