An artificial intelligence can detect diarrhoea with up to 98 per cent accuracy by analysing the sounds emanating from toilets. This skill could help us track outbreaks of diseases such as cholera. Maia Gatlin at the Georgia Institute of Technology and her colleagues collected 350 recordings of toilet-based sounds from YouTube and sound database Soundsnap – covering standard defecation, diarrhoea, urination and flatulence. The researchers then used 70 per cent of the recordings to train an AI to recognise audible differences between the four types of excretion. Once they confirmed that the AI could consistently do this with another 10 per cent of the data, they tested the AI's performance using the last 20 per cent of the recordings.

Reading Stephen Buranyi's article (Rise of the racist robots, G2, 8 August) reminded me of a discussion 30 years ago with a sixth-form class (following a viewing of Kubrick's 2001: A Space Odyssey) on whether daily contact with computers would make us more machine-like. "No," said one girl: "Since humans contaminate everything they come in contact with, we'll end up by infecting machines with our irrationalities. Percipient students are always ahead of their time. If Gatlin had not been there, Bolt would still have lost. In all the press and TV commentary, Christian Coleman, who came second, was hardly mentioned.