Get all your news in one place.
100's of premium titles.
One app.
Start reading
The Independent UK
The Independent UK
Technology
Anthony Cuthbertson

THE TRUTH ABOUT: Ai neuron freezing offers safety breakthrough - Caught on Camera

Researchers found discovered a new way to introduce safety guardrails for large language models that power apps like OpenAI's ChatGPT and Google's Gemini - (Getty/iStock)

Artificial intelligence researchers have developed a novel technique to make ChatGPT and other popular chatbots safer.

The method, referred to as “neuron freezing”, prevents users from bypassing the built-in safety filters of the large language models (LLMs) underpinning these AI tools.

Sign up to read this article
Read news from 100's of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.