Digital Trends
broadcast images as prompt toChatGPTis still a fairly new feature article , but in my own testing , it works finely most of the time . However , someone ’s just found an persona that ChatGPT ca n’t seem to handle , and it ’s decidedly not what you look .
The epitome , spot by brandon_xyzw on X ( formerly Twitter ) , presents some digital interference . It ’s nothing special , really — just a black background with some vertical lines all over it . But if you seek to show it to ChatGPT , the image weaken the chatbot each and every sentence , without fail .
Digital Trends
I tried to feed the image to ChatGPT with additional text prompts and without , as part of a conversation , or at the outset of a young Old World chat . The only reply I ’m beget is ChatGPT ’s misplay content , “ Hmm … something seems to have gone unseasonable . ” Attempting to father a unexampled response does n’t facilitate .
Whatever you do , don't show ChatGPT this imagepic.twitter.com/DwSkmz0xP6
& mdash ; Brandon ( @brandon_xyzw)January 10 , 2024
Interestingly enough , ChatGPT reply when I post it a screenshot of the tweet carry the image , and it describe it just o.k. . However , when I then tried to show it the actual prototype in that same conversation , it break again .
What ’s so special about this image that reach ChatGPT hate it so ? It ’s hard to say . I search up similar images on the web and establish that ChatGPT breaks when faced with some of them , but not all of them . It ’s most likely just a bug , given that it handled the screenshot just fine , as well as interchangeable images featuring digital noise .
I tried the image with some of the other popular chatbots , and they had no job telling me more about the image . While ChatGPT fight to respond to my prompt , Bing Chatanalyzed the image and described it to me in some detail . While Bing Chat went for an analytic thinking of the proficient sort , Google Bardstarted construe the mental image , order the pursuit : “ The colors red and dark are often used together to represent opposites or complementary forces . In this case , the ruddy and blue lines could be find out as representing convinced and negative vim , or order and topsy-turvydom . ”
Ultimately , while ChatGPT works well enough most of the time , it ’s not without fault . It sometimes forgets what it ’s allowed or not allowed to do , declining to perform simple chore that it had no problem with just two messages earlier . error with generating responses bechance quite oft too , but this particular image systematically breaks the chatbot . We ’ll have to stress this again in a match of days and see if OpenAI has desex the issue .
