https://www.aisi.gov.uk https://www.aisi.gov.uk/careers https://www.aisi.gov.uk/about https://www.aisi.gov.uk/blog https://www.aisi.gov.uk/privacy-policy https://www.aisi.gov.uk/grants https://www.aisi.gov.uk/grants/example-projects https://www.aisi.gov.uk/careers/apply https://www.aisi.gov.uk/research https://www.aisi.gov.uk/research-agenda https://www.aisi.gov.uk/frontier-ai-trends-report https://www.aisi.gov.uk/frontier-ai-trends-report/pdf https://www.aisi.gov.uk/blog/a-pipeline-for-transcript-analysis-using-inspect-scout https://www.aisi.gov.uk/blog/advanced-ai-evaluations-may-update https://www.aisi.gov.uk/blog/advancing-the-field-of-systemic-ai-safety-grants-open https://www.aisi.gov.uk/blog/advancing-voice-ai-security-with-elevenlabs https://www.aisi.gov.uk/blog/ai-and-the-future-of-work-measuring-ai-driven-productivity-gains-for-workplace-tasks https://www.aisi.gov.uk/blog/ai-safety-summit-2023 https://www.aisi.gov.uk/blog/aisis-research-direction-for-technical-solutions https://www.aisi.gov.uk/blog/an-evaluation-framework-for-ai-misuse-in-fraud-and-cybercrime https://www.aisi.gov.uk/blog/announcing-our-san-francisco-office https://www.aisi.gov.uk/blog/announcing-the-alignment-project https://www.aisi.gov.uk/blog/announcing-the-uk-and-france-ai-research-institutes-collaboration https://www.aisi.gov.uk/blog/announcing-the-uk-and-us-aisi-partnership https://www.aisi.gov.uk/blog/ask-dont-tell-reducing-sycophancy-in-large-language-models-2 https://www.aisi.gov.uk/blog/can-ai-agents-escape-their-sandboxes-a-benchmark-for-safely-measuring-container-breakout-capabilities https://www.aisi.gov.uk/blog/conference-on-frontier-ai-safety-frameworks https://www.aisi.gov.uk/blog/do-chatbots-inform-or-misinform-voters https://www.aisi.gov.uk/blog/early-insights-from-developing-question-answer-evaluations-for-frontier-ai https://www.aisi.gov.uk/blog/early-lessons-from-evaluating-frontier-ai-systems https://www.aisi.gov.uk/blog/evals-bounty https://www.aisi.gov.uk/blog/evaluating-whether-ai-models-would-sabotage-ai-safety-research https://www.aisi.gov.uk/blog/evidence-for-inference-scaling-in-ai-cyber-tasks-increased-evaluation-budgets-reveal-higher-success-rates https://www.aisi.gov.uk/blog/examining-backdoor-data-poisoning-at-scale https://www.aisi.gov.uk/blog/first-progress-report https://www.aisi.gov.uk/blog/fourth-progress-report https://www.aisi.gov.uk/blog/from-bugs-to-bypasses-adapting-vulnerability-disclosure-for-ai-safeguards https://www.aisi.gov.uk/blog/funding-60-projects-to-advance-ai-alignment-research https://www.aisi.gov.uk/blog/harnessing-frontier-ai-for-cyber-defence https://www.aisi.gov.uk/blog/how-are-ai-agents-used-evidence-from-177000-ai-agent-tools https://www.aisi.gov.uk/blog/how-do-ai-models-persuade-exploring-the-levers-of-ai-enabled-persuasion-through-large-scale-experiments https://www.aisi.gov.uk/blog/how-do-environmental-factors-impact-ai-behaviour https://www.aisi.gov.uk/blog/how-do-frontier-ai-agents-perform-in-multi-step-cyber-attack-scenarios https://www.aisi.gov.uk/blog/how-to-evaluate-control-measures-for-ai-agents https://www.aisi.gov.uk/blog/how-were-working-with-frontier-ai-developers-to-improve-model-security https://www.aisi.gov.uk/blog/how-will-ai-enable-the-crimes-of-the-future https://www.aisi.gov.uk/blog/inspect-cyber https://www.aisi.gov.uk/blog/inspect-evals https://www.aisi.gov.uk/blog/international-ai-network-consensus-and-open-questions https://www.aisi.gov.uk/blog/international-joint-testing-exercise-agentic-testing https://www.aisi.gov.uk/blog/international-scientific-report-on-the-safety-of-advanced-ai-interim-report https://www.aisi.gov.uk/blog/interviewing-researchers-on-automation https://www.aisi.gov.uk/blog/introducing-controlarena-a-library-for-running-ai-control-experiments https://www.aisi.gov.uk/blog/investigating-models-for-misalignment https://www.aisi.gov.uk/blog/llm-judges-on-trial-a-new-statistical-framework-to-assess-autograders https://www.aisi.gov.uk/blog/long-form-tasks https://www.aisi.gov.uk/blog/managing-risks-from-increasingly-capable-open-weight-ai-systems https://www.aisi.gov.uk/blog/mapping-the-limitations-of-current-ai-systems https://www.aisi.gov.uk/blog/navigating-the-uncharted-building-societal-resilience-to-frontier-ai https://www.aisi.gov.uk/blog/new-updates-to-the-aisi-challenge-fund https://www.aisi.gov.uk/blog/open-sourcing-our-testing-framework-inspect https://www.aisi.gov.uk/blog/our-2025-year-in-review https://www.aisi.gov.uk/blog/our-approach-to-ai-capability-elicitation https://www.aisi.gov.uk/blog/our-approach-to-evaluations https://www.aisi.gov.uk/blog/our-approach-to-tackling-ai-generated-child-sexual-abuse-material https://www.aisi.gov.uk/blog/our-evaluation-of-claude-mythos-previews-cyber-capabilities https://www.aisi.gov.uk/blog/our-evaluation-of-openais-gpt-5-5-cyber-capabilities https://www.aisi.gov.uk/blog/our-first-year https://www.aisi.gov.uk/blog/partnering-with-microsoft-to-strengthen-frontier-ai-safety https://www.aisi.gov.uk/blog/pre-deployment-evaluation-of-anthropics-upgraded-claude-3-5-sonnet https://www.aisi.gov.uk/blog/pre-deployment-evaluation-of-openais-o1-model https://www.aisi.gov.uk/blog/principles-for-safeguard-evaluation https://www.aisi.gov.uk/blog/replibench-measuring-autonomous-replication-capabilities-in-ai-systems https://www.aisi.gov.uk/blog/research-agenda https://www.aisi.gov.uk/blog/safety-case-template-for-inability-arguments https://www.aisi.gov.uk/blog/safety-cases-at-aisi https://www.aisi.gov.uk/blog/second-progress-report https://www.aisi.gov.uk/blog/strengthening-ai-resilience https://www.aisi.gov.uk/blog/the-inspect-sandboxing-toolkit-scalable-and-secure-ai-agent-evaluations https://www.aisi.gov.uk/blog/third-progress-report https://www.aisi.gov.uk/blog/transcript-analysis-for-ai-agent-evaluations https://www.aisi.gov.uk/blog/what-can-sandboxed-ai-agents-learn-about-their-evaluation-environments https://www.aisi.gov.uk/blog/why-i-joined-aisi---geoffrey-irving https://www.aisi.gov.uk/blog/why-were-working-on-white-box-control https://www.aisi.gov.uk/category/alignment https://www.aisi.gov.uk/category/analysis https://www.aisi.gov.uk/category/chem-bio https://www.aisi.gov.uk/category/control https://www.aisi.gov.uk/category/cyber https://www.aisi.gov.uk/category/engineering https://www.aisi.gov.uk/category/human-influence https://www.aisi.gov.uk/category/model-transparency https://www.aisi.gov.uk/category/organisation https://www.aisi.gov.uk/category/safeguards https://www.aisi.gov.uk/category/safety-cases https://www.aisi.gov.uk/category/science-of-evaluations https://www.aisi.gov.uk/category/societal-resilience https://www.aisi.gov.uk/category/strategic-awareness https://www.aisi.gov.uk/people/alan-cooney https://www.aisi.gov.uk/people/alex-remedios https://www.aisi.gov.uk/people/alexandra-souly https://www.aisi.gov.uk/people/asa-cooper-stickland https://www.aisi.gov.uk/people/ben-millwood https://www.aisi.gov.uk/people/benjamin-hilton https://www.aisi.gov.uk/people/chris-summerfield https://www.aisi.gov.uk/people/eric-winsor https://www.aisi.gov.uk/people/geoffrey-irving https://www.aisi.gov.uk/people/hannah-kirk https://www.aisi.gov.uk/people/jade-leung https://www.aisi.gov.uk/people/jake-pencharz https://www.aisi.gov.uk/people/jay-bailey https://www.aisi.gov.uk/people/jerome-wunne https://www.aisi.gov.uk/people/jerome-wynne https://www.aisi.gov.uk/people/jessica-wang https://www.aisi.gov.uk/people/marie-buhl https://www.aisi.gov.uk/people/michael-schmatz https://www.aisi.gov.uk/people/oliver-sourbut https://www.aisi.gov.uk/people/ollie-matthews https://www.aisi.gov.uk/people/robert-kirk https://www.aisi.gov.uk/people/sid-black https://www.aisi.gov.uk/people/technical-staff https://www.aisi.gov.uk/people/tomek-korbak https://www.aisi.gov.uk/people/xander-davies https://www.aisi.gov.uk/people/yarin-gal https://www.aisi.gov.uk/research/a-mathematical-philosophy-of-explanations-in-mechanistic-interpretability https://www.aisi.gov.uk/research/a-multi-turn-framework-for-evaluating-ai-misuse-in-fraud-and-cybercrime-scenarios https://www.aisi.gov.uk/research/a-sketch-of-an-ai-control-safety-case https://www.aisi.gov.uk/research/agentharm-a-benchmark-for-measuring-harmfulness-of-llm-agents https://www.aisi.gov.uk/research/aisi-frontier-ai-trends-report-2025 https://www.aisi.gov.uk/research/an-alignment-safety-case-sketch-based-on-debate https://www.aisi.gov.uk/research/an-example-safety-case-for-safeguards-against-misuse https://www.aisi.gov.uk/research/ask-dont-tell-reducing-sycophancy-in-large-language-models https://www.aisi.gov.uk/research/async-control-stress-testing-asynchronous-control-measures-for-llm-agents https://www.aisi.gov.uk/research/avoiding-obfuscation-with-prover-estimator-debate https://www.aisi.gov.uk/research/boundary-point-jailbreaking-of-black-box-llms https://www.aisi.gov.uk/research/breaking-agent-backbones-evaluating-the-security-of-backbone-llms-in-ai-agents https://www.aisi.gov.uk/research/chain-of-thought-monitorability-a-new-and-fragile-opportunity-for-ai-safety https://www.aisi.gov.uk/research/conversational-ai-increases-political-knowledge-as-effectively-as-self-directed-internet-search https://www.aisi.gov.uk/research/deep-ignorance-filtering-pretraining-data-builds-tamper-resistant-safeguards-into-open-weight-llms https://www.aisi.gov.uk/research/does-self-evaluation-enable-wireheading-in-language-models https://www.aisi.gov.uk/research/emerging-practices-in-frontier-ai-safety-frameworks https://www.aisi.gov.uk/research/evaluating-explanations-an-explanatory-virtues-framework-for-mechanistic-interpretability https://www.aisi.gov.uk/research/evaluating-whether-ai-models-would-sabotage-ai-safety-research https://www.aisi.gov.uk/research/fundamental-limitations-in-defending-llm-finetuning-apis-2 https://www.aisi.gov.uk/research/hibayes-a-hierarchical-bayesian-modeling-framework-for-ai-evaluation-statistics https://www.aisi.gov.uk/research/how-are-ai-agents-used-evidence-from-177-000-mcp-tools https://www.aisi.gov.uk/research/how-to-evaluate-control-measures-for-llm-agents-a-trajectory-from-today-to-superintelligence https://www.aisi.gov.uk/research/infusion-shaping-model-behaviour-by-editing-training-data-via-influence-functions https://www.aisi.gov.uk/research/lessons-from-a-chimp-ai-scheming-and-the-quest-for-ape-language https://www.aisi.gov.uk/research/lessons-from-studying-two-hop-latent-reasoning https://www.aisi.gov.uk/research/measuring-ai-agents-progress-on-multi-step-cyber-attack-scenarios https://www.aisi.gov.uk/research/model-tampering-attacks-enable-more-rigorous-evaluations-of-llm-capabilities-2 https://www.aisi.gov.uk/research/open-technical-problems-in-open-weight-ai-model-risk-management https://www.aisi.gov.uk/research/practical-challenges-of-control-monitoring-in-frontier-ai-deployments https://www.aisi.gov.uk/research/principles-for-evaluating-misuse-safeguards-of-frontier-ai-systems https://www.aisi.gov.uk/research/propensity-inference-environmental-contributors-to-llm-behaviour https://www.aisi.gov.uk/research/quantifying-frontier-llm-capabilities-for-container-sandbox-escape https://www.aisi.gov.uk/research/replibench-evaluating-the-autonomous-replication-capabilities-of-language-model-agents https://www.aisi.gov.uk/research/safety-case-template-for-frontier-ai-a-cyber-inability-argument-2 https://www.aisi.gov.uk/research/safety-cases-a-scalable-approach-to-frontier-ai-safety https://www.aisi.gov.uk/research/security-challenges-in-ai-agent-deployment-insights-from-a-large-scale-public-competition https://www.aisi.gov.uk/research/seven-simple-steps-for-log-analysis-in-ai-systems https://www.aisi.gov.uk/research/skewed-score-a-statistical-framework-to-assess-autograders https://www.aisi.gov.uk/research/stack-adversarial-attacks-on-llm-safeguard-pipelines https://www.aisi.gov.uk/research/the-levers-of-political-persuasion-with-conversational-ai https://www.aisi.gov.uk/research/why-human-ai-relationships-need-socioaffective-alignment-2