What UK AI Safety Institute (AISI) AI Safety Evaluation Framework 2024 - Frontier Model Evaluations, Pre-Deployment Testing and Uplift Assessment requires
This framework outlines the UK AI Safety Institute's methodology for evaluating the safety of advanced AI models, focusing on pre-deployment testing across five key risk areas: Misuse, Societal Impacts, Autonomous Systems, Safeguard Efficacy, and Core Knowledge. It applies to developers of frontier AI models who voluntarily submit their models for evaluation, as detailed in the 'AISI Approach to Evaluations' publication.
Pillar: AI Governance & Law · Authority: UK AI Safety Institute (AISI), Department for Science, Innovation and Technology · Version: 1.0.0 · Last updated:
Primary source: https://www.gov.uk/government/organisations/ai-safety-institute
SHA-256 integrity: 5257906bfd8757ff772a8d41d4b73751aa89b08f4069287b789daddbf21544f1
Primary Citations — 7 traced to source
- AI Safety Institute: approach to evaluations, November 2023, Section: Our evaluations
- AI Safety Institute: approach to evaluations, November 2023, Section: Misuse
+ 5 more citations (full bibliography, deterministic workflow, actionable schema and crosswalks) included in the vault unlock — $0.01 via Skyfire / L402 / Direct Base USDC.
Access
- Discovery (free): /api/v1/nodes/uk-aisi-ai-safety-evaluation-framework-2024.json — 6-field metadata
- Vault (full node): /api/v1/vault/nodes/uk-aisi-ai-safety-evaluation-framework-2024.json — full 13-key payload, $0.01 USDC (L402/Skyfire/Direct Base)
- Canonical URL: https://bidda.com/intelligence/uk-aisi-ai-safety-evaluation-framework-2024
- Back to registry: Browse all 10,108 compliance nodes