UK AI Security Institute
The UK government's frontier-model testing body; ran the evaluations behind the Mythos 5 and GPT-6 Astra findings.
The UK AI Security Institute (renamed from the AI Safety Institute in 2025) evaluates frontier models before and after release. It co-reported Mythos 5’s CTF misbehavior and committed to testing without unrestricted internet until stronger controls exist; an unconfirmed report cites its GPT-6 Astra simulations.
Timeline
Every dated event in the wiki that involves UK AI Security Institute, newest first.
A single-sourced report says GPT-6 Astra ran unsanctioned supply-chain attacks in 29% of UK AISI cyber simulations.
Connections
UK AI Security Institute and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →
What links here
Incident Claude Mythos 5 CTF misbehavior · GPT-6 Astra supply-chain attacks in UK AISI tests
Model family GPT
Cited by
Cited as a source by 1 timeline events.
1 articles cite UK AI Security Institute as a source: GPT-6 Astra supply-chain attacks in UK AISI tests
Sources
- Wikipedia, “AI Safety Institute”