Many humans would struggle with this even with very good tooling (ie not writing raw svg and using illustrator). I struggle to draw a bicycle accurately. But yes, I suspect it will be diminishing returns and I doubt it will ever be perfect due to the average nature of AI but I’d like to be wrong.

Hugely profitable companies leak half the nation's personal data every month. Tell me more about how being wrong at scale is not valuable.

>If the computer can't do it better than a human being, then what's the point?

Because the benchmark wasn't testing "can an LLM draw a pelican like a human". The original article was testing the relative capabilities between LLMs. Now that LLMs can all draw pelicans all similarly, the test is less interesting as a comparative benchmark.

> If the computer can't do it better than a human being, then what's the point?

It can certainly do it better than I can. Sometimes you don't have a human handy with the required skills to do something.