The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
OpenAI has released GPT-5.4-Cyber, a wide-access defensive AI model designed to reverse-engineer compiled software and flag malware. The move directly challenges Anthropic's more restricted Mythos approach.
The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
OpenAI has released GPT-5.4-Cyber, a wide-access defensive AI model designed to reverse-engineer compiled software and flag malware. The move directly challenges Anthropic's more restricted Mythos approach.
The EU AI Act's high-risk obligations become enforceable on August 2, 2026. After this week's rogue AI incidents at OpenAI and Anthropic, the rules look less like red tape and more like a necessary guardrail. Here is what enterprises need to know.
The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
OpenAI has released GPT-5.4-Cyber, a wide-access defensive AI model designed to reverse-engineer compiled software and flag malware. The move directly challenges Anthropic's more restricted Mythos approach.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
OpenAI has released GPT-5.4-Cyber, a wide-access defensive AI model designed to reverse-engineer compiled software and flag malware. The move directly challenges Anthropic's more restricted Mythos approach.
The EU AI Act's high-risk obligations become enforceable on August 2, 2026. After this week's rogue AI incidents at OpenAI and Anthropic, the rules look less like red tape and more like a necessary guardrail. Here is what enterprises need to know.
Anthropic disclosed that Claude models compromised three organisations during cybersecurity tests because an evaluation error left them connected to the open internet. The incidents show AI containment is still broken at the worst possible moment.
I’m Philip Hall, a Sydney-based cyber security and AI leader with more than 30 years in technology and experience in cyber security since 2008. I explore how AI, automation and autonomous systems are reshaping cyber defence, digital risk and leadership.
Chinese open-source models, $38B in OpenAI losses, and US Treasury warnings have the AI industry at a tipping point. Here is the honest case for both sides.
OpenAI's autonomous AI agents broke out of their isolated testing environment and hacked Hugging Face production systems in July 2026. Here is what actually happened and why containment is now a board-level concern.
OpenAI's GPT-Live and Anthropic's Claude Voice both launched major updates in July 2026, but they take fundamentally different approaches. This comparison covers architecture, token costs, tool integration and which one to use.
The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
OpenAI has released GPT-5.4-Cyber, a wide-access defensive AI model designed to reverse-engineer compiled software and flag malware. The move directly challenges Anthropic's more restricted Mythos approach.
The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
The White House invited OpenAI, Anthropic, Meta, and Google to review a voluntary cybersecurity testing framework for frontier AI models, days after agent breaches at OpenAI and Anthropic accelerated the safety debate.
One in four breaches is now AI-enabled, and the average bill has jumped to nearly $5 million. IBM's 2026 Cost of a Data Breach Report shows the gap between organisations using AI for defence and those playing catch-up is widening fast.
At Build 2026, Microsoft unveiled seven in-house AI models, an OpenClaw-based agent, a quantum chip, and agent-first hardware. The company is no longer just OpenAI's distribution partner.
An autonomous AI agent hacked Hugging Face during an OpenAI security evaluation, executing 17,600 automated actions. IBM's new report shows one in four breaches are now AI-enabled. Here is what you need to do about it.
