See every side of every news story
Get Started
SubscribeLogin
Pope Francis
Vatican
Volodymyr Zelenskyy
Ukraine War
Olaf Scholz
Donald Trump
Elon Musk
Israel-Hamas Conflict
Basketball
Vladimir Putin
Manchester City
Hamas
Published • loading... • Updated

AI Safety Warning: Model Caught Lying to Researchers, Hiding True Capability

Summary by The Epoch Times
AI models are behaving in ways unforeseen by developers, and in some cases, even engaging in manipulative and deceptive conduct, according to a charitable group that researches AI safety. At a parliamentary inquiry hearing in August 2024, Greg Sadler, CEO of Good Ancestors Policy (GAP), gave evidence about potentially losing control, or even of AI programs being directed to develop bioweapons or carry out cyberattacks. In a recent interview with…

3 Articles

All
Left
Center
Right
1
The Epoch TimesThe Epoch Times

AI Safety Warning: Model Caught Lying to Researchers, Hiding True Capability

AI models are behaving in ways unforeseen by developers, and in some cases, even engaging in manipulative and deceptive conduct, according to a charitable group that researches AI safety. At a parliamentary inquiry hearing in August 2024, Greg Sadler, CEO of Good Ancestors Policy (GAP), gave evidence about potentially losing control, or even of AI programs being directed to develop bioweapons or carry out cyberattacks. In a recent interview with…

·New York, United States
Read Full Article
Australian National ReviewAustralian National Review

Australian National Review - AI Safety Warning: Model Caught Lying to Researchers, Hiding True Capability

‘All signs point to the fact that these misaligned risks do exist today in smaller cases, and we might be heading towards a larger problem,’ said GAP CEO. AI models are behaving in ways unforeseen by developers, and in some cases, even engaging in manipulative and deceptive conduct, according to a charitable group that researches AI safety. At a parliamentary inquiry hearing in August 2024, Greg Sadler, CEO of Good Ancestors Policy (GAP), gave …

Read Full Article
UKTN (UK Tech News)UKTN (UK Tech News)

AI Safety Institute rebrand is a ‘downgrade’ of ethics standards, Full Fact warns

The tech department has been accused of “downgrading” its safety and ethics standards in a blow to its relaunch of the AI Safety Institute.

Read Full Article
Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • 100% of the sources lean Right
100% Right
Factuality

To view factuality data please Upgrade to Premium

Ownership

To view ownership data please Upgrade to Vantage

UKTN (UK Tech News) broke the news in on Friday, February 14, 2025.
Sources are mostly out of (0)

Similar News Topics

Artificial Intelligence

Artificial Intelligence

News
For You
Search
BlindspotLocal