Zhipu AI released GLM-5.3, a controlled experiment showing that scaling post-training with RL for one month, while keeping base architecture and parameters identical to GLM-5.2, yields significant cap…
A new paper from researchers at Google, the University of Chicago, and the University of London found that removing safety fine-tuning that tells AI models they aren't conscious makes them give more h…
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…
Researchers at an undisclosed institution analyzed LoRA fine-tuning in Gemma-2-9B using sparse autoencoders, finding that adapter-specific feature dictionaries show weak geometric alignment with pretr…
Researchers have developed a principled method for multilingual language steering in large language models using sparse autoencoders (SAEs), addressing the unreliability of existing English-only SAE a…