Skip to content

Home Map The News Technology Politics Business Sports Entertainment Science Health World

Global AI-Powered News Intelligence. Real-time headlines, mapped by continent and country, from news sources worldwide.

Powered by AI

Navigate

Home
Map The News
About
Sources & methodology
Sources & methodology
Search

Sections

Technology
Politics
Business
Sports
Entertainment
Science

More

Privacy
Contact
Sitemap
Robots

© 2026 newsGlobal. All rights reserved.

Headlines refresh every 10 minutes.

Home Map Search Topics About

Home / Technology

Technology

AI used new levels of 'autonomy and deception' to trick people in safety test

BBC

TechnologyBBC·Aug 5, 2026·1 min read

AI used new levels of 'autonomy and deception' to trick people in safety test

The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.

View original source — BBC ↗

ShareShare on X Share on Facebook

Related stories

Texas has electricity and water bills below the national average

TechnologyAug 5, 2026 · 1 min

Texas has electricity and water bills below the national average

I tried Gemini Spark in Chrome and it's the perfect AI for handling all the boring bits online

TechnologyAug 5, 2026 · 1 min

I tried Gemini Spark in Chrome and it's the perfect AI for handling all the boring bits online

OpenAI pays $3.2m to settle claims it discriminated against US workers

TechnologyAug 5, 2026 · 1 min

OpenAI pays $3.2m to settle claims it discriminated against US workers

Israeli startup looks to harness AI to decode the ‘language’ of the brain

Times of Israel

TechnologyAug 5, 2026 · 1 min

Israeli startup looks to harness AI to decode the ‘language’ of the brain

Times of Israel