SAE

A new method called Geometry-Guided Constraint Learning improves LLM safety classification by using sparse autoencoder (SAE) feature extraction, achieving 96-99% accuracy per category on the BeaverTai…

Humanoid robots are now commercially available for $14,000 without standardized safety testing, as robotics intelligence outpaces validation frameworks. Researchers propose a five-level taxonomy for r…

Researchers propose an empirical test for error correction in large language models, finding that residual-stream activations are robust to small perturbations and that feature-specific directions are…