Managing the risks posed by artificial intelligence is “one of the most profound responsibilities” world leaders face, according to Prime Minister Rishi Sunak.
The PM will tell a major technology summit that successfully managing AI will create major opportunities for human progress, but said governments needed to “work together to ensure it is safe”.
Mr Sunak and South Korean President Yoon Suk Yeol will co-host a virtual session on Tuesday as the two-day summit in Seoul begins with delegates from firms including Microsoft, Google DeepMind, OpenAI and Anthropic.
In his remote address, Mr Sunak is expected to say: “To unlock the benefits of AI, we must also work together to ensure it is safe. Because safe AI is innovative AI.”The summit follows the first such gathering at Bletchley Park, the home of the UK’s Second World War codebreakers, in November.Mr Sunak will say: “We made history with the Bletchley Park summit at the end of last year. Together, we committed to build a consensus on the risks of AI to develop an independent, international AI safety report and to take greater action to counter the frontier risks.“Managing the risks of AI is one of the most profound responsibilities we face. Because if we get it right, it will also create the most profound opportunities for human progress that we have seen in our lifetimes.”The summit comes as debate around the need for, and scale of, AI regulation has intensified around the world.A recent report said general purpose AI could boost wellbeing, prosperityand scientific research in the future, but also power widespread isinformationand fraud, disrupt jobs and reinforce inequality.The report was the first produced by the International Scientific Report on Advanced AI Safety and was carried out by AI experts from 30 countries – including the UK, US and China – as well as the UN and the EU.As well as highlighting the potential benefits and risks of the technology, it warns there is not universal agreement among experts on a range of topics including the state of current AI capabilities and how those could evolve over time, and the likelihood of extreme risks – such as losing control over the technology – occurring.
