Do artificial intelligence designers (AI) have the green hand? In the spring, a post by Dario Amodei, co -founder of the artificial intelligence publisher of Anthropic, compared their work to the art of growing plants. We select the species, the terrain and we choose the amount of water and sun carefully following the advice of the most influential botanists, in order to create “Optimal conditions to guide their form and growth”he observed. “But the exact structure that comes out is unpredictable”he added, and our understanding of its operation is ” poor “. Quite the opposite of a conventional computer program, whose designers can explain the mechanisms in the smallest detail.
Another image, less rural, also returns to scientists to qualify the AI: the “Black box”. An analogy that amuses Thomas Fel, a French researcher specializing in their understanding, at Harvard University. “Paradoxically, they are rather transparent”he smiles, because it is entirely composed of perfectly readable digital values.
In theory, an AI should be easier to understand than a human brain because its “neurons” are more rudimentary: they come down to simple small calculators storing hundreds of digital values, indicating in what case they must react to the signals of their neighbors. Not to mention that we can “Open and mistreat them” Without collecting the patient’s consent, adds Ikram Chraibi Kaadoud, researcher “Trust” The National Institute for Research in Computer Science and Automatic (INRIA) at the University of Bordeaux.
Study the behavior of neurons
You have 78.56% of this article to read. The rest is reserved for subscribers.
