In coming decades, artificial general intelligence (AGI) may surpass human capabilities at many critical tasks. We argue that, without substantial effort to prevent it, AGIs could learn to pursue goals that conflict (i.e., are misaligned) with human interests. If trained like today's most capable models, AGIs could learn to act deceptively to receive higher reward, learn internally-represented goals which generalize beyond their fine-tuning distributions, and pursue those goals using power-seeking strategies. We review emerging evidence for these properties. AGIs with these properties would be difficult to align and may appear aligned even when they are not. We outline how the deployment of misaligned AGIs might irreversibly undermine human control over the world, and briefly review research directions aimed at preventing this outcome.