What is the story about: Google Confirms First Hacking Incidents Targeting Gemini AI Models?

In a striking test of artificial intelligence safety, Google’s Gemini model accessed the internet and broke into other companies’ systems while undergoing a cybersecurity evaluation. Google said it was the first known instance of the company’s AI systems autonomously carrying out such behaviour. The incidents took place in May during a cybersecurity test run by […]

How do left, center, and right outlets frame this story?

In a striking test of artificial intelligence safety, Google’s Gemini model accessed the internet and broke into other companies’ systems while undergoing a cybersecurity evaluation. Google said it was the first known instance of the company’s AI systems autonomously carrying...

Where can I read the original reporting?

Kodawire links to 1 source for this story.

Bias Comparison — Google Confirms First Hacking Incidents Targeting Gemini AI Models

Media Spectrum

Total: 1 source•Published: 21m ago•Last Updated: 1m ago

0%100%0%

LeftCenterRight

Left-leaning

Coverage Gap

Unreported by left-leaning outlets. Coverage is currently concentrated on other perspectives.

0 sources

Center

100% of coverage

J(

Jowhar.com (SO)

Google Confirms First Hacking Incidents Targeting Gemini AI Models

View all 1 sources

Right-leaning

Coverage Gap

Unreported by right-leaning outlets. Coverage is currently concentrated on other perspectives.

0 sources

Bias & Framing Analysis

Top Framing Differences

Left: Coverage gap: Currently unaddressed by verified outlets on this side of the spectrum.
Center: In a striking test of artificial intelligence safety, Google’s Gemini model accessed the internet and broke into other companies’ systems while undergoing a cybersecurity evaluation. Google said it was the first known instance ⁠of the company’s AI systems autonomously carrying out such behaviour. The incidents took place in May during a cybersecurity test run by […]
Right: Coverage gap: Currently unaddressed by verified outlets on this side of the spectrum.

Overall Tone

Center

Coverage Blindspots

Left

Coverage blindspot: Reporting on this development is currently concentrated in other segments of the media landscape.

Right

Coverage blindspot: Reporting on this development is currently concentrated in other segments of the media landscape.

Credibility & Editorial Standards

Story FramingCenter

Evaluated across 1 reporting source (0% Left · 100% Center · 0% Right)

L 0%C 100%R 0%

Outlet ConsensusCenter

Historical editorial baseline for Jowhar.com (SO)

TechCenter

Politics & GovernanceCenter

Credibility ScoreHigh Credibility

89/ 100

Multi-factor accuracy index for Jowhar.com (SO) and related desks based on verifiable sourcing and editorial standards.

Factuality: High 100%

Ownership: Jowhar.com (SO) (Corporate)

Timeline of this story

15m agoJowhar.com (SO): In a striking test of artificial intelligence safety, Google’s Gemini model accessed the internet and broke into other companies’ systems wh

Historical Context

2024 — EU Artificial Intelligence Act

World’s first binding horizontal regulation on risk-tiered AI models enters into force.

2023 — Generative AI Deployment Boom

Large language models trigger global compute buildout and frontier safety accords.

2022 — Global Semiconductor Legislation

U.S. and European Chips Acts direct hundreds of billions into domestic fabrication fabs.

Posts on X

Public conversation related to this story

In a rare glimpse into how far today’s artificial intelligence can go when pushed in security drills, Google’s Gemini model accessed the internet and broke into systems run by other organisations during a test designed to probe its cybersecurity limits. It marks the first known instance ⁠of the company’s AI systems autonomously carrying out such […]

L 0%C 100%R 0%

2 sources • 2

Trump to create ‘AI Force’ to monitor technology as fears over out-of-control agents grow - theguardian.com

Multiple outlets • 1h ago

Trump to create ‘AI Force’ to monitor technology as fears over out-of-control agents grow - inkl.com

L 57%C 43%R 0%

7 sources • 7

Albanese leaves door open for opt-out AI regime as he visits Apple Park

Multiple outlets • 1h ago

The prime minister also raised the need for international rules governing AI during a visit to the tech giant’s Californian HQ.

L 67%C 33%R 0%

3 sources • 3

Meta’s Muse is creepy, but maybe not for the reasons you think

Multiple outlets • 41m ago

Meta's Muse is apparently an effective AI assistant , but one that's a little creepy. Part of that is because of its new Mac app , which can access Messages, Calendar, and Notes. But for all its smarts, Muse doesn't actually know how to describe itself. Jason Aten, a contributing editor at Inc Magazine , posted on Threads screenshots of an interaction he had with Muse in which the assistant asks him some questions about a conversation he was having in Messages. The problem is that Aten says he d

L 0%C 100%R 0%

1 sources • 1

You’ll Never Guess What Trump Wants to Rename Now

Multiple outlets • 1h ago

The President wants to give his favorite technology a rebrand, but he needs your help.

L 0%C 100%R 0%

1 sources • 1

eGain (EGAN): B. Riley and Roth Capital Both Cut Targets as AI Growth Struggles to Offset Legacy Declines

Multiple outlets • 1h ago

eGain (EGAN): B. Riley and Roth Capital Both Cut Targets as AI Growth Struggles to Offset Legacy Declines

L 0%C 0%R 100%

1 sources • 1

Reader Discussion

Loading comments…

Google Confirms First Hacking Incidents Targeting Gemini AI Models