Concrete problems in AI safety

Concrete problems in AI safety Amodei, Olah, et al., arXiv 2016 This paper examines the potential for accidents in machine learning based systems, and the possible prevention mechanisms we can put … Read more


AI won’t solve everything

If you spend enough time listening to AI researchers it’s easy to start believing that if only we gave AI researchers enough funding and computational resources, they would eventually manage to solve everything else. Physics. Neuroscience. Economics. You ... (more…)

Read more »