Yandex has started an experiment aimed at studying the ability of artificial intelligence (AI) to manifest consciousness. The research is being conducted together with neurobiologist and academician of the Russian Academy of Sciences Konstantin Anokhin.
The first stage consisted of testing the basic language model. The researchers checked the formation of AI preferences without additional training. It turned out that the neural network does not have such preferences. The second stage involves researchers encouraging AI to reason. The main task of the project is to train the neural network to form beliefs similar to human ones.
There is hope that if we start training a neural network on its own reasoning, we can create a model that will have its own point of view. Not imposed and not its imitation. But internal beliefs. Or maybe even something more than that.
