Photo of the Day – Oh, Bard…
I love playing around with new AI stuff. Some of it is good (Midjourney/ChatGPT) some of it is bad and sometimes it’s downright hit and miss. Regardless of the outcome, it’s always fun to experiment. Recently Google added image upload to Bard, their AI chat, and you can have it do things like describe the content of the image.
Now knowing the Bard has a tendency, even with normal chat, to find facts out of the ordinary, I’m curious to see how it goes with some of my drawings. To be fair, it was promising at first, but then… well… things got a little “imaginative”. So here’s one example:
“The picture you sent me shows an aerial view of the city with tall buildings and a cruise ship in the middle. The city is located on a peninsula, and the water on the left side of the image is a bay. The buildings in the city are mostly tall skyscrapers, and there are some smaller ones as well. The cruise ship in the center of the image is white, and has a blue stripe on the side. There were several people on the yacht, and they were standing on the deck.
The sky in the image is blue, and there are some clouds. The sun is shining, and the light is reflecting off the water in the bay. The overall impression of the image is one of a modern city with a beautiful skyline.
Here are some additional details about the image:
Picture taken during the day, in the evening.
The weather is clear and sunny.
The water in the bay is light blue.
The sky is clear blue.
The city is surrounded by mountains.
I hope this description is useful.”
So the question is… did Bard “imagine” what was outside the picture or take it as Hong Kong and therefore depict aspects of the location, even though it’s not in the frame… hmm…
