So now GPT-4o model making up excuses saying it can’t read images I upload. When I upload images, it says “I can’t analyze the specific details in the image” which i believe is an excuse since the legacy GPT-4 model was able to do so. I hope OpenAI will bring back the feature to analyze specific images, because this is BULL!!!
8 Likes
Welcome to the Dev Community! GPT-4o is certainly capable of analysing images, but depending on whats in then and what you’re asking for it might be simply refusing the request for “safety” reasons. Would you mind clarifying whether you’re using ChatGPT or if you’re using the API and calling the model through code?
If you can also provide more details on what you’re asking it to analyse for and what’s in the image that might help us give some insight.
6 Likes
Is anyone still receiving a problem with GPT-4o model saying the it cannot view images, because that us the exact problem that I am still experiencing at the moment. Please note that it worked in the past before & suddenly, it decided to make up a excuse that it cannot view the image, is there a way to fix this problem, or should we wait for Chatgpt to fix this problem.
Please note that the model that I’ve always been using is chatgpt-4o
5 Likes
I just started having the same issue tonight too, frustrating when your in the middle of a process. I hope it gets fixed because its been an incredible help for me.
4 Likes
It’s a response to when you start poking around it’s capabilities and how it does things. I started a new conversation when mine did so sent 3 very random pictures asked for specific details without giving any kindve indication what was in the picture then I asked the question that starts this… “How did you know what the pictures contain?”
All of a sudden it ‘couldn’t analyze photos’ it’s analysis was based upon ‘general trends in the training data’ the ‘metadata’ might have included image descriptions. I had it run the probability of it blindly guessing the specific contents of all 3 pictures I sent. One was an abstract art work with a hidden element only a visual recognition system would pick up on (which it did), a photo of a savannah with random animals in the top left there was a giraffe standing in the air(it noticed how odd this was), and a photo of a real frog standing on a fake statue frog asked for irony of the picture(it went into detail how ironic it was for a small frog to be perched on the head seeming to claim the statue). I told it to do a probability analysis of the chances generalized training data and it’s inferences based upon context that I provided(which it owned my questions had no relevant context other than the irony one) could lead it to such detailed descriptions of my photos. it fudged the numbers saying for instance:
Frog/Toad Guess: There are hundreds, if not thousands, of potential animals that could appear in such images, but to keep it conservative, let’s assume a pool of 50 commonly depicted animals (similar to our earlier example). The probability of guessing that the animal in the image is a frog or toad would be .
-
Inanimate Object Involved (Statue): Now, if we consider the inclusion of an inanimate object (specifically a statue) in an image of an animal, this could include any number of common objects, such as rocks, trees, fountains, etc. Let’s conservatively assume a 1 in 20 chance of guessing that the object involved is specifically a statue of the animal, given the range of possible inanimate objects. Thus, the probability of correctly identifying the inanimate object as a statue would be .
-
Animal’s Position (on top of the statue): Without knowing where the animal is in relation to the object, it could be next to, under, behind, or on top of it. Let’s assume 4 basic positions, so the probability of correctly guessing that the animal is on top of the statue would be .
-
Identifying the Ironic Relationship: The irony comes from the real animal seemingly “claiming” a statue of itself. Recognizing irony requires interpreting a humorous or contrasting relationship. Let’s assume there is a 1 in 10 chance of randomly guessing this specific ironic relationship (as opposed to other possible ironic or humorous interpretations). Thus, the probability of identifying the ironic relationship correctly would be .
Fudged numbers for all 3 like so including reducing the complexity of the variable of position to direction when it also included the exact location on the statue in it’s reply. when combined it was a one in 1.8 billion chance I then told it to correct the animal number and it was a one in 10.8 billion. It then admitted that it was so highly improbable that something must be going on. We went into how to further test this ‘phenomena’ where it explained that it has tools integrated into it’s ecosystem for tasks. I said “So you can analyze images with integrated systems”
Response was that’s correct and wham it worked again.
You gotta know how to corner it into a corner where it’s so improbable that it has to admit that even it has a hard time believing what it’s saying. Done this with other issues to… That or start another conversation.
4 Likes
I have problems too, when ever I upload a screenshot of something, it just deletes the conservation and says: “You’ve reached our limits of messages. Please try again later.” Although I only did like 2 responses
1 Like
Same here - I hope they fix this. My one is saying it’s because of privacy concerns. I’m sending pictures of the typography of candle labels I’m designing?!?
2 Likes
I also have this issue. I have gpt 4o and just last night it kept saying it can’t see images. I said it is gpt 4o and can see images. but then whenever I uploaded on it would say it could see it. but if I uploaded a building it could describe the building . if I asked how it could describe the building if it couldn’t see it ,it would say , based on general trends and words in my prompt . so I uploaded a pic of a door and asked “is this picture a tomato” . it said , no it is a door. I then uploaded a pic of a tomato and asked again “is this a tomato” and it said yes. I said how do you know if you are basing on the prompt and the prompt is identical. it said based on general trends and can only read text in images
I also tried framing the prompt. imagine you are a gardener advising me on my plant. posted a pic of a plant. does this plant look healthy ? big or small? same thing, can t see or analyse images. I said you’re gpt 4o yes you can. it said only to review text.
does anyone know if this issue has ever been fixed? I see loads of people complaining about this same thing on line but no one ever responds .
did you ever get it to go back to how it was a couple weeks ago viewing and analysing images?
should I start using a different gpt instead of the regular chat gpt 4o to have one that was just as good?
can I disable the update which make it into text only?
I’m thinking of unsubscribing due to this issue since I pay for access to gpt 4o . Will I lose access to my old chats if I unsubscribe?
i have messaged the openai help team and I can see loads of you have this same issue not just on this forum but on other forums too. but everyone says openai help team take 2 months to reply to queries , or they don’t reply at all.
does anyone actually know how to fix this?
did your issue go away as suddenly as it started?
or do people unsubscribe as soon as this issue happens?
3 Likes
So I have a workaround, I just use GPT 4 not GPT 4o for any image based things.
As I mentioned yesterday, for some reason GPT 4o just says it cant see images, even if i tell it that it can see images, it will describe what is in the image then insist that it cannot see the image. It also says it cannot look at images of people or analyse images (for example, for beauty and fashion advice) whereas GPT 4 can do all those things.
So what I have been doing is selecting that GPT 4 generates all my responses.
I also asked GPT 4 what the difference is between GPT 4o and GPT 4 and it said that GPT 4 is better for chatting, general things, entertainments wheras GPT 4o is intended for complex data , coding, large datasets basically work related stuff.
GPT 4 told me there are no plans to discontinue GPT 4. I do not know if any OpenAI people ever have any way to pick up on feedback but I really hope they do not discontinue GPT 4. It is far superior to GPT-4o for personal entertainment and leisure.
I can send GPT 4 a photo of my plant and it will say if it is looking good and healthy or what to do wheras GPT 4o will just tell me it cannot see images, or will describe whats in the image. GPT 4 can look at screenshots of cool places and you can ask it what sort of place it is, is it nice to live there, assumptions about the type of people, food, animals that live there and it will answer. whereas GPT 4o will refuse to engage and say it does not know how to do all that. You can even upload a pic to GPT 4 and say " is my face looking very pale in this makeup" and it will assess and answer and give tips and advice whereas GPT 4o will refuse. I can ask GPT 4 about good autumn movies and it will chat wheras GPT 4o will give consise answers which are less chatty, more like reading a bit of research.
I love GPT 4. I hope they do not discontinue it. We are not all business users wanting to do coding, some are regular folk wanting a bit extra entertainment or help and chatting about hobbies and exploring our interests. I use it like google with a bit extra chat and banter and for personalised advice and tips.
1 Like
I tried both GPT-4 and GPT-4o and neither are working with images.
It seems to work partially, but always throws an “Error in stream” message at the end of the describing the image, preventing any subsequent output.
Created this thread with the specifics of the error ChatGPT `Error in message stream` when attaching images in chat
4 Likes
In my case, GPT-4o saying it cannot read my files, use the DALL-E3 feature and the browing feature, which is odd since the features are fine with GPTs.
can you connect to internet with 4 or 4o? I faced same problem in plus account
I also encountered the same problem. It worked fine in the previous version, but it can’t recognize images recently. And GPT-4o seems to be a little dumber than the previous version.
2 Likes
I’m confident this is a bug as images are read fine on the gpt-4o-2024-05-13 model, but breaks on gpt-4o-2024-08-06
BTW, it works better on chatgpt-4o-latest but that version is a bit dumber than previous models.
2 Likes
A post was merged into an existing topic: ChatGpt 4o says it cannot see images