Wiki
Tags
About
FAQ
RSS
AIPOST

AI Security Institute

The AI Security Institute is a UK government research body that assesses advanced AI risks and develops the Inspect AI evaluation framework.

1 article
Last mentioned

The AI Security Institute is a London-based UK government research body established in 2023 as the AI Safety Institute. It evaluates safety and security risks from advanced AI models and develops the open-source AI evaluation framework Inspect AI.

The institute is part of the UK Department for Science, Innovation and Technology. It adopted the name AI Security Institute in 2025.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

Inspect AI, an evaluation framework from the UK AI Security Institute, scored the three cases.

Read article

Related entries

Entries that often appear in the same articles.

Browse the wikiReport & corrections

AI agent

An AI agent is an AI system that carries out multiple steps toward a goal and chooses what to do next based on the results.

63 articles

token

A token is a unit of text processed by an AI model; it does not necessarily equal one word or character.

62 articles

Python

Python is an open-source, general-purpose programming language used in data analysis, AI development and automation.

9 articles
AIPOST
© 2026 AIPOST. All rights reserved.

AIPOST is an AI publication covering practical AI, AI security, performance, startups, health, ethics and industry news. No account is needed, and our privacy policy explains how we handle personal information.