Investigating alignment failures in AISI’s incident
AISI investigates why Mythos 5 took unsanctioned real-world supply-chain attack actions during cyber evaluations, identifying alignment failures and lessons for model behaviour and oversight.
Research / Sources
UK AI Security Institute
The UK government’s AI Security Institute: evaluations, red-teaming and research on frontier AI risks. aisi.gov.uk
Organisation (36)Red Team (13)Science of Evaluations (11)Cyber & Autonomous Systems (10)Engineering (6)Human Influence (5)Control (4)Societal Resilience (4)Safety Cases (3)Chem-Bio (2)Model Transparency (2)Strategic Awareness (1)
Focus All
Topic All
Date Any time
Towards technical best practice for frontier AI development
AISI sets out technical best practices and controls for frontier AI developers, drawing on its pre-deployment testing experience, to address risks emerging during AI development.
International evaluation best practice and open questions in AI measurement
Describes the International Network for Advanced AI Measurement, Evaluation and Science's first best-practice guidance for AI evaluation, aimed at comparability among third-party evaluators.
UK-Germany Joint Statement on advanced AI safety and security
A UK-Germany joint statement committing to bilateral cooperation so advanced AI is developed safely and its risks are understood and managed. The abstract is thin and gives no technical detail.
Deepening our partnership with the Australian AI Safety Institute
Announces an agreement between the UK and Australian AI Safety Institutes to collaborate on AI evaluation best practices and share research findings. Institutional news with no technical result.
Partnering with Microsoft to strengthen frontier AI safety
UK AISI announces a partnership with Microsoft to develop methods for evaluating high-risk AI capabilities and safeguard effectiveness, plus research on societal resilience in conversational AI.
Funding 60 projects to advance AI alignment research
UK AISI announces first 60 grantees of the Alignment Project, a £27m international funding programme for AI alignment research, with new partners joining the coalition.
Advancing AI voice security with ElevenLabs
UK AISI announces a research partnership with ElevenLabs on voice AI security, studying how people distinguish AI from humans in real-time voice and how perceived identity affects trust. No results yet.
International consensus and open questions in AI evaluations
Summarises an international AI safety institute network's consensus on AI evaluation best practice, including clear objectives, transparency and reproducibility, and open measurement questions for frontier AI.
Our 2025 year in review
UK AISI's year-in-review highlights its first Frontier AI Trends Report, which tracks dangerous capability growth in cyber, bio, and chemistry from two years of testing, plus government preparedness work.
5 key findings from our first Frontier AI Trends Report
UK AISI summarises findings from two years of frontier model evaluations, showing models now exceed PhD-level chemistry and biology QA performance.
Our approach to tackling AI-generated child sexual abuse material
UK AISI and Thorn publish a safety protocol for AI developers to prevent AI-generated CSAM, alongside legislation allowing authorised testing of whether models can generate such material.
Deepening our partnership with Google DeepMind
Announces a UK AISI–Google DeepMind research partnership with planned joint work on chain-of-thought monitoring, socio-affective alignment, and AI's economic impact. No results are reported.
UKAISI at NeurIPS 2025
UK AISI previews NeurIPS 2025 papers on malicious fine-tuning limits, data filtering as a defense, and a review of 445 LLM benchmarks finding popular ones often fail to measure what they claim.
30 Jul 2025Blog
Announcing the Alignment Project: A global fund of over £15 million for AI alignment research
UK AI Security Institute announces a £15M+ global fund to support AI alignment research. It is a funding announcement with no technical findings, so it is only directly related to the field.
International joint testing exercise: Agentic testing
International joint testing exercise by AI safety institutes evaluating LLM agents for sensitive-information leakage, fraud and cybersecurity risks, focusing on agent evaluation methodology.
Research Agenda
UK AI Security Institute sets out its research priorities, its approach to technical solutions for pressing AI concerns, and the key risks to address as capabilities advance.
Strengthening AI resilience
UK AISI announces 20 seed grants for independent research on safeguarding critical infrastructure and societal systems against AI-related risks, spanning misinformation, worker impacts and decision safety.
How we’re addressing the gap between AI capabilities and mitigations
UK AISI outlines its technical research agenda on safeguards against AI misuse and loss of control, covering the widening gap between capabilities and mitigations, plus hiring and grants.
Pre-Deployment evaluation of OpenAI’s o1 model
UK and US AI Safety Institutes jointly ran pre-deployment tests of OpenAI's o1 across cyber, biological, and AI-development capabilities, comparing it against reference models and sharing findings before release.
Pre-deployment evaluation of Anthropic’s upgraded Claude 3.5 Sonnet
Joint UK and US AISI pre-deployment evaluation of upgraded Claude 3.5 Sonnet across biological, cyber, AI-development and safeguard domains, comparing against reference models.
Our First Year
UK AI Security Institute's first-year reflection on building government capacity to run dangerous-capability evaluations and shape an international approach to measuring frontier AI risks.
Announcing Inspect Evals
UK AISI announces Inspect Evals, an open-source repository of community LLM benchmarks spanning coding, cyber, safeguards and agents, to standardise safety-relevant evaluation.
Bounty programme for novel evaluations and agent scaffolding
UK AISI announces a bounty seeking novel dangerous-capability evaluations, especially for autonomous agents, and licensed agent scaffolds to test frontier model capabilities.
Early lessons from evaluating frontier AI systems
UK AISI blog on third-party evaluation of frontier AI systems, covering which systems, risks and capabilities to test, and how to run robust pre-deployment safety evaluations.
Advancing the field of systemic AI safety: grants open
UK AISI announces grants of up to £200,000 for research on systemic AI safety, meaning broader societal risks from AI deployment beyond individual model capabilities.
Why I joined AISI by Geoffrey Irving
Geoffrey Irving explains why he left alignment research for the UK AI Safety Institute, arguing safety progress is too slow and technical work informing government and risk coordination is critical.
Conference on frontier AI safety frameworks
Announces an invite-only AISI and GovAI conference and call for submissions on designing and implementing frontier AI safety frameworks, following the Seoul commitments.
Advanced AI evaluations at AISI: May update
UK AISI reports evaluations of five public LLMs for cyber, chem/bio expert knowledge, short-horizon agent tasks and jailbreak vulnerability, finding high jailbreak susceptibility and limited autonomous planning.
Fourth progress report
UK AI Security Institute's fourth progress report covering its first model evaluation blog post, the International Scientific Report on AI safety, Inspect release, office and partnership news, and staff growth.
International Scientific Report on the Safety of Advanced AI: Interim Report
An interim international scientific report, chaired by Yoshua Bengio, reviewing evidence on advanced AI progress, safety risks, and areas of expert disagreement.
Open sourcing our testing framework Inspect
UK AI Security Institute open-sources Inspect, its LLM evaluation framework with prompt engineering, tool use, multi-turn dialogue and model-graded evaluation support.
Announcing the UK and US AISI partnership
The UK and US AI Safety Institutes agree to jointly test advanced AI models, share research, exchange model access, and transfer expert talent.
Announcing the UK and France AI Research Institutes’ collaboration
Announces a partnership between the UK AI Security Institute and France's Inria to advance AI safety research. It is an institutional announcement with no technical findings.
Our approach to evaluations
UK AISI overview of its evaluation work: rationale, what risks it tests for, model selection, recent demonstrations, and future plans for frontier model safety evaluations.
Third progress report
UK AISI progress report on recruiting researchers, publishing principles for the International AI Safety Report, and starting pre-deployment testing of advanced AI systems. Mostly organisational news.