Last week, Lee Se-dol, the South Korean Go best who lost in a actual antagonism against DeepMind’s bogus intelligence algorithm AlphaGo in 2016, declared his retirement from able play.

“With the debut of AI in Go games, I’ve accomplished that I’m not at the top even if I become the number one through agitated efforts,” Lee told the Yonhap news agencyEven if I become the number one, there is an entity that cannot be defeated.”

Predictably, Se-dol’s comments bound made the rounds across arresting tech publications, some of them using amazing account with AI ascendancy themes.

Since the dawn of AI, games have been one of the main benchmarks to appraise the adeptness of algorithms. And thanks to advances in deep learning and reinforcement learning, AI advisers are creating programs that can master very complicated games and beat the most acclimatized players across the world. Uninformed analysts have been acrimonious up on these successes to advance that AI is acceptable smarter than humans.

But at the same time, contemporary AI fails miserably at some of the most basic that every human can perform.

This begs the question, does arrive a game prove anything? And if not, how can you admeasurement the level of intelligence of an AI system?

Take the afterward example. In the account below, you’re presented with three problems and their solution. There’s also a fourth task that hasn’t been solved. Can you guess the solution?