{{Short description|British research organisation}}{{Infobox organization | name = AI Security Institute | formation = {{start date and age|2023|11}} | logo = AI security institute logo.svg | services = AI safety research | parent_organization = Department of Science, Innovation and Technology | website = {{url|https://www.aisi.gov.uk}} }} The '''AI Security Institute''' ('''AISI''') is a research organisation under the Department for Science, Innovation and Technology, UK, that aims "to equip governments with a scientific understanding of the risks posed by advanced AI".<ref>{{Cite web |title=AISI |url=https://www.gov.uk/government/organisations/ai-security-institute |access-date=20 February 2026 |website=Government of UK}}</ref> It conducts research and develop and test mitigations. Previously, it was known as the AI Safety Institute.<ref>{{Cite web |title=Written statements - Written questions, answers and statements - UK Parliament |url=https://questions-statements.parliament.uk/written-statements/detail/2025-02-24/hcws462 |access-date=2026-03-23 |website=questions-statements.parliament.uk |language=en}}</ref> Its creation followed world's first major AI Safety Summit that was held in Bletchley Park in 2023.<ref name=":0">{{Cite news |title=Britain is the closest the world has to an AI safety inspector |url=https://www.economist.com/britain/2026/02/19/britain-is-the-closest-the-world-has-to-an-ai-safety-inspector |access-date=2026-02-20 |work=The Economist |issn=0013-0613}}</ref> The institute's professed goal is "building the world's leading understanding of advanced AI risks and solutions, to inform governments so they can keep the public safe". It is designed like a startup in the government "combining the authority of government with the expertise and agility of the private sector".<ref name=":1">{{Cite web |title=Equipping governments with a scientific understanding of the risks posed by advanced AI |url=https://www.aisi.gov.uk/about |website=AI Security Institute}}</ref>
AISI has made access agreements with Anthropic, Google and OpenAI to test their models before release.<ref name=":0" /> It has an open source platform called Inspect that permits companies, governments and academics to run standardised safety tests for AI usage.<ref name=":0" /> Among the works AISI has done is the reported detection of multiple serious vulnerabilities that could enable development of biological weapons; the vulnerabilities were fixed before the model was launched.<ref name=":0" />
It conducts research on diverse fields of AI application. One study by AISI found that LLMs post-trained for political persuasiveness became systematically less accurate and up to 51% more persuasive on political issues.<ref>{{Cite journal |date=2025-12-04 |title=The levers of political persuasion with conversational artificial intelligence |url=https://www.science.org/doi/10.1126/science.aea3884 |journal=Science}}</ref> AISI has also worked on the usage of AI for emotional needs. It found that nearly 10 percent of UK citizens used systems like chatbots for emotional purposes on a weekly basis.<ref>{{Cite news |last=Milmo |first=Dan |last2= |first2= |date=18 December 2025 |title=Third of UK citizens have used AI for emotional support, research reveals |url=https://www.theguardian.com/technology/2025/dec/18/artificial-intelligence-uk-emotional-support-research |access-date=2026-02-20 |work=The Guardian |language=en-GB |issn=0261-3077}}</ref> It found that "systems are now outperforming <abbr>PhD</abbr>-level researchers on scientific knowledge tests and helping non-experts succeed at lab work that would previously have been out of reach" in a report published in December 2025.<ref>AISI. ''[https://www.aisi.gov.uk/frontier-ai-trends-report/pdf Frontier AI Trends Report]''. December 2025. retrieved on 20 February 2026</ref>
Former chief AI officer of GCHQ Adam Beaumont is the institution's interim director. UK prime minister's AI advisor Jade Leung is the chief technology officer.<ref name=":1" />
==See also== * Alan Turing Institute, UK institute for data science and AI * Artificial intelligence safety institute
== References == <references />
== External links ==
* {{Official website|}}
Category:Artificial intelligence organizations Category:Artificial intelligence