Home›Concepts
Concepts
Concepts
How AI works, in plain language: from the artificial neuron to the Transformer, pre-training and reasoning models.
Total 25 · Clear filters
Red teamingRed teaming is the practice of actively probing a model for harmful or unwanted behaviour before deployment. A 2022 method by Perez and colleagues automated it by using one language model to generate test cases for another.Mechanistic interpretabilityMechanistic interpretability explains model behaviour by finding the internal computations and features that produce it. Work on superposition and sparse autoencoders shows how many features can be packed into few neurons.JailbreakA jailbreak is an adversarial prompt that gets a safety-trained model to produce behaviour its training was meant to prevent. A 2023 analysis by Wei et al. traced these failures to competing objectives and mismatched generalization.Semantic WebThe Semantic Web is a W3C standards effort that uses RDF and OWL to describe data so different applications, enterprises and communities can share and reuse information, moving from research toward practical tools.Visual odometryVisual odometry lets a rover measure how far it actually moved by tracking features in camera images taken before and after a short drive, instead of trusting wheel turns. NASA's Mars Exploration Rovers were the first to demonstrate it.