A new wave of research sheds light on how LLMs reason with probabilities, creatively plan ahead, and think in universal concepts—revealing both their potential and their risks. Why are AI chatbots so intelligent—capable of understanding complex ideas, crafting surprisingly good short stories, and intuitively grasping what users mean? The truth is, we don’t fully know. Large language models “think” in ways that don’t look very human. Their outputs are formed from billions of mathematical signals bouncing through layers of neural networks powered by computers of unprecedented power and speed, and most of that activity remains invisible or inscrutable to AI researchers. Click here to read the full article