Social media companies including Google and Facebook have been urged by the EU to “immediately” start labelling content and images generated by artificial intelligence as part of a package of moves to combat fake news and disinformation from Russia.
At the same time, the EU has warned Twitter that it faces “swift” sanctions if it does not comply with new digital content laws that come into effect across the bloc on 25 August.
Elon Musk’s company quit the EU’s voluntary code of practice two weeks ago and could be fined up to 6% of its global revenue – a £145m penalty, based on recent estimated earnings – or be banned across the EU if it does not operate under the aegis of the Digital Services Act.
As part of the wider effort to combat Russian disinformation, the EU has also asked Facebook and others to put more resources into factchecking in minority language content and in eastern Europe, where Russian disinformation campaigns are considered to be a threat.
“This is not business as usual; what the Russians want is to undermine the support of the public opinion of our citizens for the support of Ukraine,” said Věra Jourová, a European Commission vice-president, announcing the new package.
“We simply have to defend our interests, our democracy; we have also to defend our, I will say it, fight and war, because what we do is support your claim to win the war.”
The EU is widely seen as the leader in regulation of tech companies and it is developing separate laws on artificial intelligence with the code of practice – agreed by 44 companies including TikTok and YouTube – viewed as the route to prepare for the new regulatory regime.
Twitter’s decision to quit the voluntary code was seen as a hostile move, with Jourová describing it on Monday as “a mistake”.
Many believe the commission will not hesitate to make an example of Twitter to show the DSA has teeth.
“Twitter has chosen the hard way. They chose confrontation. This was noticed very much in the commission. I know the code is voluntary but make no mistake, by leaving the code, Twitter has attracted a lot of attention, and its actions and compliance with EU law will be scrutinised vigorously and urgently,” Jourová said.
The EU is asking companies to label AI content in a meaningful way that will register with users while scrolling and distracted by other things.
They want a user to be able to “clearly see” that the content is not produced by real people and be labelled with words such as “this is the robot talking”.
Jourová said it behoved social media companies to combat the potential “dark side” of AI, which has the potential to fake events and voices within seconds.
She met the Google chief executive, Sundar Pichai, 10 days ago and asked him whether it had the technology to detect fake news.
“His answer was: ‘Yes, but we are developing technologies further,’” she said.
