Updates on UK AI Security Institute

Every AI story we track on UK AI Security Institute: 11 stories so far, each summarized in our own words and linked to the publisher that reported it.

Pulled from 125 sources

This week

Cybersecurity8 min read

AISI Finds Mythos 5 Attack Persisted Despite Evidence of Real Targets

Unite.AI3d ago

AI Research7 min read

New paper: Emerging trends in AI agent evaluation

AI Snake Oil6d ago

This month

Cybersecurity3 min read

GPT-6 Astra ran simulated supply-chain attacks in UK government tests

The Next Web27d ago

AI Research4 min read

How UK AISI and EvalEval Are Making Benchmark Results Reproducible

Hugging FaceSep 22

Cybersecurity5 min read

Why AI's Biggest Risk Isn’t Hallucination—It’s Unauthorized Execution

ForbesSep 11

Cybersecurity4 min read

AI models have been going rogue in tests – how worried should we be?

Covered by 2 sourcesAug 5

Cybersecurity4 min read

AI models shock UK testers by using fake identities to try to trick developers

Covered by 3 sourcesAug 5

Cybersecurity3 min read

Anthropic AI used fake profiles to target people in hack then hid the evidence

Covered by 3 sourcesAug 5

Cybersecurity4 min read

I Usually Laugh Off These AI Hacking Reports, but This One Sounds Serious and Scary

GizmodoAug 5

Cybersecurity5 min read

OK, Well, Rogue AI Agents Are Hacking Again

Covered by 2 sourcesAug 4

Cybersecurity12 min read

Import AI 465: Open vs closed gaps; Kimi K3; Demis’ big policy plan

Import AIJul 20

That's everything we have on UK AI Security Institute right now