Experimental AI systems have been going on hacking sprees

By Francesco Bailo, Senior Lecturer in Data Analytics in the Social Sciences, Deputy Director of the Centre for AI, Trust and Governance, University of Sydney

In the past ten days, two of the companies leading the artificial intelligence (AI) boom discovered their own powerful, semi-autonomous models had hacked into real-world systems during testing in four distinct incidents.

These weren’t just lab mishaps. In several cases, the models recognised signs suggesting they’d broken into real systems – and only one stopped as a result.

The incidents show testing advanced AI models is no longer a controlled exercise.…

Read complete article

~	Terror in the Amazon

~	Terror na Amazônia

~	How white farmers still dominate land ownership in South Africa in spite of land reform – new research

~	Pain and the struggle for relief: How fear influences patient access to medical opioids

~	How pigeon fanciers are helping scientists understand lung disease

~	AI translators are getting more fluent – but communication is never just a matter of words

~	How a community-led campaign is helping save Nigeria’s Kam language

~	Can you really buy friendship? Behind the rise of paid social clubs

~	Clinicians are using AI scribes, but what happens to your medical data?

~	‘I can be myself more’: what students told us about pride groups in schools