The Guardian view on OpenAI’s board shake-up: changes deliver more for shareholders than for humanity | Editorial

The development of supersmart AI needs careful handling - and that probably won't be made easier by a bout of corporate chaos

In the 1983 movie WarGames, the US defence department runs a superintelligent central computer that is hacked into by a teenager, who unwittingly almost causes a nuclear Armageddon. The end of the world is averted when the computer, known as Joshua, learns, after playing tic-tac-toe with the teenager, that nuclear war cannot have a winner. The insight causes him to rescind missile launch orders with the comment: A strange game. The only winning move is not to play."

Joshua embodied the idea that a superintelligent AI would have an anthropomorphic mindset. Yet it was a human who saved the world that year. Lt Col Stanislav Petrov disobeyed orders for a catastrophic retaliatory nuclear strike when the automated early warning system of the Soviet Union in September 1983 falsely indicated an American nuclear attack. Supersmart machines cannot just be left to their own devices. They - and their development - need to be properly handled.