Modality-agnostic decoders leverage modality-invariant representations in human subjects' brain activity to predict stimuli irrespective of their modality (image, text, mental imagery).
Security researchers used GPT-5.4 and Claude Opus 4.6 in an open-source harness to reproduce Anthropic's Mythos vulnerability ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results