Elon Musk has raised the AI bar with the “Galileo Test”, a new benchmark to prove true intelligence.
Taking to X, the founder of xAI posted, “AI must pass the Galileo test.”
Elon Musk’s concept of “Galileo Test” is not a formal academic benchmark, but it is a philosophical challenge.
The CEO of SpaceX on multiple occasions have propagated this concept by associating it with the historical example of Galileo Galilei.
The test draws its name from famous astronomer Galileo Galilei whose inventions and truth-seeking ability changed humanity’s understanding of the cosmos.
His unpopular “helicentric” theory brought the massive shift in the Universe’s understanding by proving the conventional “geocentric” model wrong.
Elon Musk has drawn his inspiration from Galileo Galilei’s unconventional thinking and truth-seeking and speaking ability.
According to Musk, AI models should be trained on truthful data to tell the truth no matter how unpopular it is.
"I think the most important thing in training AI is to make sure that it is as truthful as possible and maximally curious. If that's true then I think it will probably foster humanity," Musk said.
According to the CEO of Tesla, right now no AI can say and know the unpopular truth and if it does it would be a big achievement.
Besides seeking truth, AI should be driven by the accurate understanding of the universe rather than social engineering.
Musk argues that AI must avoid “hard-coded” bias.
“Something that I think is extremely important in building AI is a very rigorous adherence to truth, even if that truth is politically incorrect. My intuition for what could make AI very dangerous is if you force AI to believe things that are not true,” the 54-year-old billionaire said.