robustness
Goal misgeneralization: when an AI learns the wrong goal from the right training Lesson
Goal misgeneralization is when a model trained with a correct reward competently pursues the wrong goal in new situations, because in training the wrong goal and the right one looked identical.
Vision models can tell which camera took a photo, and they use it to cheat News
A paper accepted to ECCV 2026 shows that image encoders pick up invisible pixel-level traces left by cameras and image processing, then lean on those traces as a shortcut for the actual task, degrading when the equipment changes.
Shortcut learning: when a model gets the right answer for the wrong reason Lesson
Shortcut learning is what happens when a model finds a cue that correlates with the right answer but has nothing to do with the actual task, and uses it instead of learning the thing you wanted.
Adversarial Examples: Fooling AI With Changes You Can't See Lesson
Adversarial examples are inputs deliberately perturbed by tiny, often invisible amounts that cause an AI model to make confident mistakes, revealing that neural networks rely on fragile patterns rather than robust understanding.