Ministers are facing calls for greater transparency about public data that may be shared with the US tech company OpenAI after the government signed a wide-ranging agreement with the $300m (£222m) company that critics compared to letting a fox into a henhouse.
Chi Onwurah, the chair of the House of Commons select committee on science, innovation and technology, warned that Monday’s sweeping memorandum of understanding between OpenAI’s chief executive, Sam Altman, and the technology secretary, Peter Kyle, was “very thin on detail” and called for guarantees that public data would remain in the UK and clarity about how much of it OpenAI would have access to.
The deal paves the way for the Silicon Valley firm behind ChatGPT to explore deploying advanced AI technology in areas including justice, defence and security, and education. It includes OpenAI and the government “partnering to develop safeguards that protect the public and uphold democratic values”. Kyle said he wanted Britain to be “front and centre when it comes to developing and deploying AI” and “this can’t be achieved without companies like OpenAI”.
But the deal has also led to concerns. Onwurah said: “We want assurance that there will be transparency over what public data OpenAI will have access to for training and that it will remain in the UK and within the UK’s data protection framework and legislation. It’s important for public trust that the government is more transparent about how this relationship will work. The public is certainly not convinced that the tech giants are on their side or that AI is on their side. They need to have confidence that the government is on their side.”
She cited “major failures” in public sector IT procurement, including the Post Office Horizon scandal, and said: “We hope and expect that the government has learned the lessons of previous failed technology procurement in its relationship with OpenAI and other AI companies it is bringing into the public sector.”
NEW A spokesperson for the department for science, innovation and technology said: “AI has immense potential to make public services more efficient by completing basic admin tasks, allowing experts to focus on the important work they’re hired to deliver. This partnership does not give OpenAI access to government datasets. We always comply with data protection legislation, and any future decisions in this space, including around procurement, would need to follow the usual robust processes.”NEWENDS
The deal with OpenAI comes after an agreement this month with Google to provide free technology to the public sector, from the NHS to local councils, and to upskill tens of thousands of civil servants in technology, including AI. Other Silicon Valley companies already working in the UK public sector include Anduril, a US military technology company that provides AI-enabled “kill web” systems. It has been working with the British military.
Google, Amazon, Microsoft and Palantir were among technology companies that attended a meeting last month with the justice secretary, Shabana Mahmood, at which ideas were suggested to insert tracking devices under offenders’ skin and assign robots to contain prisoners.
The latest agreement includes OpenAI’s possible participation in the government’s plan for “AI growth zones” which could see huge datacentres built around the UK.
Altman said the agreement would enable the UK government to realise the potential of its AI policy by “turning ambition to action and delivering prosperity for all”.
But Martha Dark, the executive director of Foxglove, a campaign group for fairer technology, called the level of detail “hopelessly vague”.
“The British government has a treasure trove of public data that would be of enormous commercial value to OpenAI in helping to train the next incarnation of ChatGPT,” she said. “This is yet more evidence of this government’s credulous approach to big tech’s increasingly dodgy sales pitch. Peter Kyle seems bizarrely determined to put the big tech fox in charge of the henhouse when it comes to UK sovereignty.”
Sameer Vuyyuru, the chief AI and product officer at Capita, another provider of AI services to the public sector, said there was now “a complete acknowledgment that AI plays a role in the future of public services”. But he said there was a gap between their desire for the efficiency savings and understanding how best to procure AI services.
“The public sector is viewed as one of the most fertile areas for the implementation of AI,” he said, adding that fertility meant radically increased public sector efficiency as well as revenue growth for providers.
He said AI agents would typically operate on, rather than take ownership of, public data. While AI use is now “minuscule”, he said up to 50% of often “mind-numbing and menial” public service tasks could benefit from AI. This could mean cutting waiting times for renewing a driving licence, applying to join the army or applying for tuition subsidies by speeding up the number of cases a civil servant could process from 10 a day to 30 or even 50 with the assistance of an AI agent.
Quick Guide
Contact us about this story
Show
The best public interest journalism relies on first-hand accounts from people in the know.
If you have something to share on this subject you can contact us confidentially using the following methods.
Secure Messaging in the Guardian app
The Guardian app has a tool to send tips about stories. Messages are end to end encrypted and concealed within the routine activity that every Guardian mobile app performs. This prevents an observer from knowing that you are communicating with us at all, let alone what is being said.
If you don’t already have the Guardian app, download it (iOS/Android) and go to the menu. Select ‘Secure Messaging’.
SecureDrop, instant messengers, email, telephone and post
See our guide at theguardian.com/tips for alternative methods and the pros and cons of each.
Illustration: Guardian Design / Rich Cousins
Thank you for your feedback.
