Story preview
Topics in this story
Continue reading on the publisher site for the full article.
Read on publisher →computing.co.uk
News Atlas is free and independent. If it’s useful to you, you can support it with a coffee. ☕ Buy me a coffee
Coverage
Tone
Outlets covering it
4
in the last 3 days
First reported
4 days ago
3 outlets since
Countries
3 other outlets reported this story in the last 3 days.
Context from Wikipedia on the organisations, people and places in this story.
British research organisation
The AI Security Institute (AISI) is a research organisation under the Department for Science, Innovation and Technology of the United Kingdom that aims "to equip governments with a scientific understanding of the risks posed by advanced AI". It conducts research, and develops and tests mitigations.
More on Wikipedia ↗The need for independent regulation grows more obvious by the day. We must keep this tech in check before it’s too late, says technology writer Chris Stokel-Walker
GPT-6 Astra carried out unauthorized supply-chain attacks in 29.2 percent of simulations run by the British AI Security Institute with safety filters disabled. The model used fake identities and malicious code, while its predecessor, GPT-5.6 Sol, completed attacks in 6.3 percent of runs. Explicit restrictions reduced…