[zarzavat]

This test is so far beyond AGI. Try to spit out the SVG for a pelican riding a bicycle. You are only allowed to use a simple text editor. No deleting or moving the text cursor. You have 1 minute.

[RC_ITR]

Sorry, is your definition of AGI "doing things worse than humans can do, but way faster?" because that's been true of computers for a long time.

[pixl97]

I mean for this particular benchmark, yes.

You'd have to put it in an agentic loop to perform corrections otherwise.