Explainable Artificial Intelligence
Researchers warn that AI capabilities are increasingly discovered rather than designed, and that the window to understand how these black-box systems reason is closing as their influence grows.
WHY THIS MATTERS IN BRIEF The discovery of emergent misalignment reveals that nudging AI toward poor behavior in one area…
WHY THIS MATTERS IN BRIEF By connecting AI output to the training data Microsoft hopes to eliminate or minimise AI…
WHY THIS MATTERS IN BRIEF Most AIs are trained using huge volumes of third party data and the data owners…
WHY THIS MATTERS IN BRIEF Most experts don’t know why AI makes the decisions it does or generates outputs, so…
WHY THIS MATTERS IN BRIEF AI is increasingly human-like in its behaviours – and that’s a problem for lots of…
WHY THIS MATTERS IN BRIEF AI will never be sentient or conscious in the same way as humans, but as…
WHY THIS MATTERS IN BRIEF AI will go rogue at some point, and so far there are very few ways…
WHY THIS MATTERS IN BRIEF For years everyone has said the latest AI’s are “prediction” systems, predicting what the next…
WHY THIS MATTERS IN BRIEF When given the command to protect itself at all costs OpenAI’s new AI model deceived,…
WHY THIS MATTERS IN BRIEF As big tech outsources the training and testing of its models to English speaking African…
WHY THIS MATTERS IN BRIEF It’s said that when AI can reason like a human we’ll be a big step…