It'd be kinda funny if they asked each AI every day and updated the clocks/rationale accordingly.
They do (with only one AI though):
"How does it work?
Every night, a script runs that asks Gemini to search the web for the latest AI news—both hype and criticism. Based on the sentiment and economic indicators it finds, it updates the predicted "burst date" and explains its reasoning."
the LLM doesn't have the concept of time and it doesn't incorporate new data, unless it's put into the context, so I don't see the point of this suggestion.
The whole thing is a joke anyways. The numbers are meaningless. The inconsistency in output from day to day highlights that even more.