International
The Morning Science

What science found today

‹
 

Topic

Interpretability

3 stories about Interpretability that passed the news check, newest first.

  1. Research ·

    Brain researchers afflict LLMs with 'injuries' similar to those of stroke victims to unpack AI language mechanisms

    Researchers used lesion maps from human aphasia and stroke patients as an external reference for interpreting language models.

    Artificial Intelligence - Tech Topics · 2 sources

  2. Research ·

    This AI ‘mechanic’ can peer inside the black box of other neural networks

    Nature reports on an AI 'mechanic' that can inspect the internal workings of other neural networks.

    nature.com

  3. Research ·

    AI agents are developing odd dialects humans struggle to follow

    Reports say AI agents are developing odd dialects that humans struggle to follow.

    News on Artificial Intelligence and Machine Learning