[sanbor]

I have a different point of view. This was a test to see if the AI could perform a specific task. Asking AI to draw a pelican riding a bike is another test. I find the experiment interesting because it proves that currently LLMs are not able to perform a simple task reliably for a long period of time.

If the journalist was not asking the right questions, or was too obvious the article was PR it’s another thing (I haven’t read WSJ’s piece, only the original post by Anthropic)