I uploaded a simple spreadsheet that was 8 rows and 12 columns. Not even 100 full cells. They were filled with plain text numbers and names, and a few dozen had green blocks, otherwise no other info/styling and no formulas. I asked ChatGPT “how many cells are green.” It told me 13 (there were over 30). I uploaded a photo. Still couldn’t do it.

I understand there are things a typical LLM can do and things that it cannot, this is mostly just because I figured it couldn’t do it and I just wanted to see what would happen. But the average person is not really given much information on the constraints and all of these companies are promising the moon with these tools.

Short version: It definitely did not have more common sense or information than a human, and we all know it sure would have given a very confident answer about conditions in the area to this person that were likely not correct. Definitely incorrect if it’s based off a photo.

In my experience when it has to crawl the Internet it’s particularly flaky. The other day I queried who won which awards in the game awards. 3 different models got it wrong, all of them omitted at least 2 categories. You could throw a rock on a search engine and find 80 lists ready to go.