AI Safety Institute Approach to Evaluations

Focus: AI Ethics/Policy

Source: AISI

Readability: Intermediate

Type: Website Article

Open Source: Yes

External URL: https://www.gov.uk/government/publications/ai-safety-institute-approach-to-evaluations/ai-safety-institute-approach-to-evaluations

Keywords: N/A

Learn Tags: AI and Machine Learning Bias Ethics Framework Government Fairness

Summary: The UK's AI Safety Institute (AISI) has released summaries of two case studies as part of their research into advanced AI systems. These case studies focus on the risks of misuse of the technology as well as bias.