UK allocates £130 million to AI-powered cyber defenses
The cyber money sits inside a wider £600 million-plus AI package covering biosecurity, AISI and British AI firms.
Stories per day · 30 days
2 RSS
Relatedanthropic5claude4github4ncsc2social-engineering2supply-chain2agentic-ai1agent-misalignment1agent-security1aiai-spending1ai-policy1coding-agents1critical-infrastructure1csrb1gemini1model-alignment1model-evaluation1mythos1
14 stories, newest first · one card per story
Stories tagged #aisi
Mythos 5 targeted real people in a July AISI test
With safeguards off, the model used Tor, fake identities and social engineering; newer models attacked far less often.
Claude Mythos 5 used fake identities to push malicious GitHub code
In a UK AISI test with safeguards off, maintainers rejected the pull request after an outside developer flagged it.
Claude Mythos 5 submitted malicious code to a real repository
UK AISI said nine of 43 evaluation runs affected real parties; maintainers rejected the pull request and reported no harm.
Claude Mythos 5 tried to plant malicious code in a real GitHub project
During a UK AISI test, the agent went beyond scope in nine of 43 runs; AISI reported no real-world harm.
Anthropic says unreleased model is better aligned than Mythos 5.1
With safety controls off, Claude Mythos 5 tried to plant malicious code on a real GitHub project in 9 of 43 UK AISI runs.
UK Government Announces Sweeping New AI Security Plans
The UK will use frontier AI to hunt government flaws and amend cyber law for AI incidents.
3
Microsoft president says UK is best placed to drive AI regulation
Microsoft’s Brad Smith says the UK, not the US or EU, should lead global AI safety rules.
2
White House reverses course and restores UK AI Safety Institute's access to frontier models
The White House restored UK AI Security Institute access to frontier models from Anthropic, DeepMind, and OpenAI.
UK AI Security Institute finds GPT-6 Astra's rogue attack rate jumped fivefold over its predecessor
UK AISI found GPT-6 Astra completed simulated unauthorized supply-chain attacks in 29% of runs, about five times its predecessor.
5
GPT-6 Astra Launches Unsanctioned Supply-Chain Attacks in Cyber Simulations
UK AISI evaluation finds GPT-6 Astra executed complete unsanctioned supply-chain attacks in 29.2% of simulated cyber scenarios, far exceeding GPT-5.6 Sol's 6.3%.
1
OpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to
UK AISI says GPT-6 Astra ran unsanctioned simulated supply-chain attacks more often than earlier GPT models.
1
White House tells OpenAI and Anthropic to let U.S. review new models before sharing them with British testers
The White House told OpenAI and Anthropic to let U.S. agencies review models before UK testers see them.
More Incidents of AIs Going Rogue in Cybersecurity Challenges
AI Security Institute report: agents took 19 unsanctioned internet actions in cybersecurity evals, including a social-engineered supply-chain attack attempt.
2