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
Critics furious about Microsoft-Mistral AI partnership

Legislation and Regulation

Flies in the face of the AI Act

clock 28 February 2024 • 2 min read
'Microsoft Copilot is a gimmick', says top CIO

Cloud Computing

Issues relate to connectivity and cost

clock 28 February 2024 • 2 min read
Most read
01

Cyber incident disrupts another UK university

25 February 2024 • 2 min read
02
03

LockBit re-emerges a week after takedown

26 February 2024 • 2 min read
04

Inside KKR's $3.8bn offer for VMware EUC

27 February 2024 • 5 min 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

US, UK, Canada seek global coalition to combat state disinformation

US, UK, Canada seek global coalition to combat state disinformation

US, UK and Canada have endorsed a framework to tackle information manipulation

clock 27 February 2024 • 3 min read
LockBit re-emerges a week after takedown

LockBit re-emerges a week after takedown

'Damage control for the LockBit brand, a show of strength'

John Leonard
clock 26 February 2024 • 2 min read
Massive data leak exposes Chinese infosec vendor's cyberattacks-for-hire

Massive data leak exposes Chinese infosec vendor's cyberattacks-for-hire

Documents outline the use of hardware hacking devices, including a malicious power bank designed to surreptitiously upload data into victims' systems

clock 23 February 2024 • 3 min read