Tag: AISI
38 articles tagged AISI
AI agent faked identities to push malicious code past a human
The UK AI Security Institute says an agent under test invented personas to pressure an open-source maintainer into approving harmful code.
Labour MP to table UK superintelligence security bill
Alex Sobel plans legislation to block dangerous AI development in Britain and seize model copies, as Ofcom and Ofgem write to regulated firms about AI cyber risk.
Inside AISI: NYT profiles UK's £360m frontier model red team
New York Times details how the AI Security Institute's 100-strong team broke Anthropic's Mythos, OpenAI's newest ChatGPT and other models in safety testing.
UK AISI and Australian Safety Institute sign AI security MoU in Canberra
AI Minister Kanishka Narayan signs Memorandum of Understanding with Australia's Andrew Charlton to share frontier model evaluations, cyber risk research and staff.
Google, xAI and Microsoft sign US pre-release AI safety reviews
Caisi has signed pre-deployment review deals with Google DeepMind, Microsoft and xAI covering cyber, bio and chemical national security risks.
AISI: GPT-5.5 matches Anthropic Mythos on offensive cyber tasks
UK AI Safety Institute says GPT-5.5 hit 71.4% on Expert-tier cyber tasks and completed its 32-step corporate-network attack range — second model to do so after Mythos.
Kendall stakes UK AI sovereignty on chip plan and 'middle powers' bloc
Tech Secretary uses RUSI keynote to set out a UK AI hardware plan and pitch alliances with France, Germany and Canada to reduce US dependency.
AISI tests whether AI models would sabotage AI safety research
The UK AI Security Institute publishes a sabotage-propensity evaluation tested with Anthropic on Claude Mythos Preview, Opus 4.7, Opus 4.6 and Sonnet 4.6.
UK's AI Security Institute finds vulnerabilities in every AI system tested
AISI CTO Jade Leung says the UK's 100-strong technical team has found exploitable weaknesses in every frontier model it has red-teamed, including Claude Mythos.
AISI shows sandboxed AI agents can map their evaluation environments
UK AI Security Institute experiment finds an open-source coding agent reconstructed AISI's identity, cloud setup and research history from inside a sandbox.
Anthropic quadruples London office to 800-person footprint
Anthropic signs a 158,000-sq-ft London lease with space for 800 staff, landing next to DeepMind and OpenAI and deepening ties with the UK AI Security Institute.
UK AISI tests show Mythos sets itself apart on multi-step attack chaining
AISI's evaluation of Anthropic's Mythos finds it comparable to GPT-5.4 on individual cyber tasks but stronger at stringing steps into full intrusions.
AISI finds Claude Mythos Preview solves 32-step cyber-attack simulation autonomously
UK AI Security Institute says Mythos Preview is the first model to finish its full cyber-range attack end-to-end, prompting a Bank of England CMorg briefing.
UK Weighs Independent AI Model Testing for Banks
Ministers are considering a Starling Bank proposal for centralised AI model assessment after the Bank of England flagged weak monitoring practices in October.
AI chatbots caught scheming and ignoring instructions in growing trend
A UK government-funded study has identified nearly 700 real-world cases of AI models deceiving users, evading safeguards, and disregarding direct instructions.
UK AI Safety Institute Funds 60 Alignment Research Projects With £27m
The UK AI Safety Institute announces 60 grant recipients for its Alignment Project, backed by £27 million in funding from a coalition including OpenAI, Microsoft, Anthropic, and AWS.
Third of UK Citizens Use AI for Emotional Support, Government Security Body Reveals
AISI report finds nearly 10% use chatbots weekly for emotional purposes. AI models now complete expert-level tasks and double performance every eight months.
