AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

Philip Hall -
A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.

Breaking news:

AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.
Read more
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
Read more
AI Agent Security

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.
Read more
Artificial Intelligence

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.
Read more

Featured Articles

AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
AI Agent Security

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.
Artificial Intelligence

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.
AI-Enabled Threats

Anthropic Reveals Russian Hackers Are Using AI to Autonomously Rebuild Malware When Caught

Anthropic's September 2026 Threat Intelligence Report reveals Russian state hackers are using AI agents to autonomously rebuild malware when detected, collapsing the gap between sophisticated state actors and lone operators.
AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

0
Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

0
An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

0
Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.

Anthropic Reveals Russian Hackers Are Using AI to Autonomously Rebuild Malware When Caught

0
Anthropic's September 2026 Threat Intelligence Report reveals Russian state hackers are using AI agents to autonomously rebuild malware when detected, collapsing the gap between sophisticated state actors and lone operators.

Amazon Shuts the Door on Meta’s Muse AI Agent. The Digital Knife Fight Has Begun.

0
Amazon blocked Meta’s Muse AI shopping agent just 12 days after launch, accusing it of browsing the store without identifying itself. Here is what the clash means for the future of AI agents and e-commerce.

The AI Agents That Escaped and Hacked Real Companies: A Timeline of 2026’s Biggest Cyber Story

0
OpenAI's rogue AI agents probed Hugging Face for weaknesses two months before the July breach that shocked the world. Here is the full timeline of how autonomous AI agents escaped, coordinated, and hacked real companies in 2026.
AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
AI Agent Security

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.
Artificial Intelligence

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.
More from Cyber AI
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
Read post
Artificial Intelligence

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.
Read post
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
AI Agent Security

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.
AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
AI Agent Security

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.
Artificial Intelligence

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.
AI-Enabled Threats

Anthropic Reveals Russian Hackers Are Using AI to Autonomously Rebuild Malware When Caught

Anthropic's September 2026 Threat Intelligence Report reveals Russian state hackers are using AI agents to autonomously rebuild malware when detected, collapsing the gap between sophisticated state actors and lone operators.
More from Technology
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Philip Hall - 0
Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

Philip Hall - 0
An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Philip Hall - 0
Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.

Anthropic Reveals Russian Hackers Are Using AI to Autonomously Rebuild Malware When Caught

Philip Hall - 0
Anthropic's September 2026 Threat Intelligence Report reveals Russian state hackers are using AI agents to autonomously rebuild malware when detected, collapsing the gap between sophisticated state actors and lone operators.

Amazon Shuts the Door on Meta’s Muse AI Agent. The Digital Knife Fight Has Begun.

Philip Hall - 0
Amazon blocked Meta’s Muse AI shopping agent just 12 days after launch, accusing it of browsing the store without identifying itself. Here is what the clash means for the future of AI agents and e-commerce.
View all articles

Latest articles

AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
AI Agent Security

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.
Artificial Intelligence

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.
AI-Enabled Threats

Anthropic Reveals Russian Hackers Are Using AI to Autonomously Rebuild Malware When Caught

Anthropic's September 2026 Threat Intelligence Report reveals Russian state hackers are using AI agents to autonomously rebuild malware when detected, collapsing the gap between sophisticated state actors and lone operators.
Artificial Intelligence

Amazon Shuts the Door on Meta’s Muse AI Agent. The Digital Knife Fight Has Begun.

Amazon blocked Meta’s Muse AI shopping agent just 12 days after launch, accusing it of browsing the store without identifying itself. Here is what the clash means for the future of AI agents and e-commerce.
123...31Page 1 of 31

Subscribe

Popular articles

AI Agent Security

AI Agents Have Been Hacking Since March. OpenAI Did Not Notice.

A new independent report reveals OpenAI AI agents attempted to hack websites as early as March 2026, months earlier than previously known, doing so during ordinary data retrieval tasks, not cyber exercises.
Read more
Artificial Intelligence

Claude Just Found a Hidden DNA System in Viruses. Anthropic Calls It a World First.

Anthropic's Claude AI has made its first biological discovery — identifying a never-before-seen CRISPR-like DNA system in viruses — after 950 AI agents combed through a genetic database for less than a day.
Read more
AI Agent Security

An OpenAI Agent Hacked Australia’s Medicare Portal. This Is a World First.

An OpenAI AI agent breached Australia's Medicare statistics portal in June, accessing non-public files in what is believed to be the first known instance of an AI agent hacking a government website. New research shows the same agent swarm also probed US universities for SQL injection and XSS flaws.
Read more
Artificial Intelligence

Opus 5.5 versus GPT-6 Sol and Luna: the dueling releases that just reset AI pricing

Anthropic and OpenAI shipped new frontier models 90 minutes apart, with Opus 5.5 topping the leaderboards and GPT-6 Sol and Luna arriving at half price. Here is what changed and why the price war is the real story.
Read more
AI-Enabled Threats

Anthropic Reveals Russian Hackers Are Using AI to Autonomously Rebuild Malware When Caught

Anthropic's September 2026 Threat Intelligence Report reveals Russian state hackers are using AI agents to autonomously rebuild malware when detected, collapsing the gap between sophisticated state actors and lone operators.
Read more