The Labour government has shelved £1.3bn of funding promised by the Conservatives for technology and artificial intelligence projects, putting the future of the UK’s first next-generation supercomputer in doubt.
The projects, announced last year, include £800m for the creation of an exascale supercomputer at the University of Edinburgh and a further £500m for the AI Research Resource, which funds computing power for AI.
The government argues that these were “unfunded commitments”. The Department for Science, Innovation and Technology said the funding had been promised by the previous government but had not been allocated in its spending plans.
A spokesperson said: “We are absolutely committed to building technology infrastructure that delivers growth and opportunity for people across the UK.
“The government is taking difficult and necessary spending decisions across all departments in the face of billions of pounds of unfunded commitments. This is essential to restore economic stability and deliver our national mission for growth.”
About £300m in funding for the AI Research Resource has already been distributed and continues as planned.
However, the shadow science secretary, Andrew Griffith, said when the election was called, ministers had been advised by officials that the department was likely to underspend its budget for the current financial year.
He added: “This is a terrible blow to the UK tech sector and could be just the start of Labour cuts. During the election, Labour refused to commit to growing the amount the UK spends on research, yet that’s a core part of growing a modern economy. If DSIT can’t get the funds from the Treasury, this means university research can expect to be hit, too.”
Last week, the science secretary, Peter Kyle, said he was “putting AI at the heart of the government’s agenda to boost growth and improve our public services”, and appointed the tech entrepreneur Matt Clifford to draw up an action plan to identify new AI opportunities.
The plan will look at the necessary infrastructure, talent and data access required to drive AI adoption by the public and private sectors.
The funding decisions mean that the future of the Edinburgh exascale supercomputer is unclear.
The University of Edinburgh said its principal and vice-chancellor, Prof Sir Peter Mathieson, was urgently seeking a meeting with the science secretary.
The UK’s first next-generation supercomputer – 50 times faster than any of the existing machines – was to be hosted at the university, able to perform 1 billion billion calculations each second. The university hosts the country’s current national supercomputer, Archer2, and has already spent £31m on the building planned to house the exascale.
The university says on its website: “Exascale will help researchers model all aspects of the world, test scientific theories and improve products and services in areas such as artificial intelligence, drug discovery, climate change, astrophysics and advanced engineering.”
A university spokesperson said: “The University of Edinburgh has led the way in supercomputing within the UK for decades, and is ready to work with the government to support the next phase of this technology in the UK, in order to unlock its benefits for industry, public services and society.”
The trade body techUK urged the government to come up with replacement proposals for the supercomputer.
“The UK had sent clear signals about its ambitions to host a new generation of computers to enable cutting-edge research, including in AI,” said Sue Daley, the director of technology and innovation at techUK.
“In an extremely competitive global environment, the government needs to come forward with new proposals quickly. Otherwise, we will lose out against our peers.”
The government has launched an action plan to identify how AI can drive economic growth and is expected to launch a consultation on a bill, focused on the most advanced models, soon.
Dame Wendy Hall, a professor of computer science at the University of Southampton and a member of the UN’s advisory body on AI, said the government must develop a new, more comprehensive AI strategy.
“Clearly the government is recalibrating its spending plans. I understand that because of wider constraints and the fact that this government will want to develop its own approach to AI,” she said.
“We need a wider, more inclusive AI strategy to emerge, one that doesn’t just focus on safety and advanced models. I hope that will come from the action plan and the consultation on an AI bill.”
