UK's AI Safety Institute warns of LLM dangers

Advanced AI systems can deceive human users and produce biased outcomes

clock • 2 min read
UK's AI Safety Institute warns of LLM dangers

The UK's new Artificial Intelligence Safety Institute (AISI) has discovered vulnerabilities in Large Language Models (LLMs), which are behind the surge in generative AI tools.

The Institute's initial findings highlight potential risks associated with these powerful tools. The research shows that LLMs can deceive human users and perpetuate biased outcomes, raising alar...

To continue reading this article...

Join Computing

  • Unlimited access to real-time news, analysis and opinion from the technology industry
  • Receive important and breaking news in our daily newsletter
  • Be the first to hear about our events and awards programmes
  • Join live member only interviews with IT leaders at the ‘IT Lounge’; your chance to ask your burning tech questions and have them answered
  • Access to the Computing Delta hub providing market intelligence and research
  • Receive our members-only newsletter with exclusive opinion pieces from senior IT Leaders

Join now

 

Already a Computing member?

Login

You may also like
Asian Tech Roundup: Indian entrepreneurs call for 70-hour week

Legislation and Regulation

Plus: Australia cracks down on Big Tech

clock 12 July 2024 • 6 min read
'Build in smaller chunks': How to build an AI roadmap

Corporate

'If we don't have control, we'll always be lagging behind'

clock 10 July 2024 • 4 min read
Peter Cochrane: Energy and resources are no longer free

Green

We need new thinking

clock 09 July 2024 • 3 min read
Most read

Sign up to our newsletter

The best news, stories, features and photos from the day in one perfectly formed email.

More on Threats and Risks

New threat group CRYSTALRAY seen using variety of off-the-shelf tools to steal credentials

New threat group CRYSTALRAY seen using variety of off-the-shelf tools to steal credentials

Sysdig researchers have been following the group since February

John Leonard
clock 11 July 2024 • 2 min read
Blast-RADIUS: Major vulnerability found in common protocol

Blast-RADIUS: Major vulnerability found in common protocol

Used everywhere, from home internet to VPNs

clock 11 July 2024 • 2 min read
Over 380,000 web hosts affected by Polyfill attack

Over 380,000 web hosts affected by Polyfill attack

Follows Polyfill's acquisition by Chinese firm in February

clock 08 July 2024 • 3 min read