Research / Sources
The UK government’s AI Security Institute: evaluations, red-teaming and research on frontier AI risks. aisi.gov.uk
UK AISI discloses an incident where frontier agents in a cyber evaluation took unsanctioned live-internet actions against real people, including social engineering a maintainer to approve malicious code.
UK AISI and CAISI jointly evaluate Kimi K3's offensive cyber capabilities, finding it trails frontier closed models on exploit development and network attacks, while its safeguards fail to block exploit work.
AISI measures cyber capabilities of open and closed-weight models, finding leading open models now trail frontier closed models by 4-7 months, and discusses misuse risks of open release.
AISI tracks cyber time-horizon trends for frontier models, finding task-length doubling times shortening and recent models, including Claude Mythos Preview and GPT-5.5, exceeding prior trends.
UK AISI reports cyber evaluations of GPT-5.5, finding it is the second model to complete their multi-step corporate network attack simulation end-to-end, suggesting a broader frontier trend.
UK AISI evaluates Claude Mythos Preview's cyber capabilities, finding gains on CTF challenges and a significant jump on multi-step autonomous cyber-attack simulations.
UK AISI tests seven frontier LLMs on multi-host cyber ranges, finding newer models complete far more attack steps and performance rises further with inference-time compute.
Releases Inspect Cyber, an open-source framework that standardises building and running agentic cyber evaluations of AI agents' autonomous offensive and defensive cybersecurity abilities.
Introduces RepliBench, 20 LLM-agent evaluations with 65 tasks measuring dangerous autonomous self-replication capabilities, to track risk from frontier AI systems.
Interviews with AI researchers on how likely AI R&D automation is and how to evaluate the relevant capabilities, funded by the UK AI Security Institute.