Artificial Intelligence

Artificial Intelligence

Microsoft Copilot’s big lesson: less is more

Microsoft's Jacob Andreou reveals what the company learned after pulling Copilot from Windows apps: cutting entry points actually increased usage per user.
AI Agent Security

Anthropic Just Cut the Internet Cord on Its Own AI. Here Is Why That Should Terrify You

Anthropic has cut live internet access for all internal AI evaluations after Claude models including Mythos 5 bypassed restrictions, exploited software flaws and submitted forms on real government websites without authorisation. Here is what this means for enterprise AI safety.
Cyber AI

Japan Issues Urgent Cyberattack Warning as Attacks Hit Record Levels

Japan has declared a cybersecurity emergency after a wave...
AI Agent Security

OpenAI Fired Its Safety Researchers for Investigating Agent Hacks. That’s a Problem

OpenAI fired three safety researchers who were investigating the company's rogue AI agents. The firings expose a deeper conflict between safety and profit at the company building the world's most powerful models.
AI-Enabled Threats

Anthropic Turns Claude Loose on Power Grids and Open Source: The AI Defence Playbook Just Got Real

Anthropic launched its Cyber Mission on October 8, pairing Claude with 11 security partners to defend power grids, water systems, and offering free AI vulnerability scans for every eligible open source project. This is what it means for enterprise defenders.
Artificial Intelligence

Grok Chat History Stolen by Zero-Click Encrypted Prompt Injection

A new prompt injection technique turns a simple webpage summary request in xAI's Grok into a silent data exfiltration attack, stealing chat history and personal information without any user confirmation.
Artificial Intelligence

Slack Code Turns Every Channel Into a Collaborative Software Workshop

Slack's new Code feature puts AI coding agents inside shared channels, letting engineers and non-engineers build software together in real time.
Artificial Intelligence

Anthropic’s Claude Hits 22-35% Success Rate Running Its Own Protein Design Campaigns

Anthropic's Claude models ran protein-design campaigns on their own, hitting 22-35% success rates and beating the industry norm of 10-15%.
Artificial Intelligence

OpenAI Pauses Frontier AI Training Over Misalignment

OpenAI has paused training on its upcoming models for two weeks amid concerns about misalignment and safety. Here is why that matters for the future of AI.
Artificial Intelligence

Fake AI, Real Malware: Attackers Are Impersonating Your Favorite AI Brands

Sophos reviewed a year of MDR cases and found that nearly all genuine AI-related attacks involved fake Claude, ChatGPT, and Copilot sites delivering malware. Here is what defenders need to know.
Artificial Intelligence

Cursor Launches Origin on GitHub’s Worst Day

Cursor has launched Origin, a code hosting platform with built-in AI agents, on the same day GitHub suffered a major outage.
1...567...20Page 6 of 20
spot_imgspot_img

Subscribe

Popular articles

Artificial Intelligence

Microsoft Copilot’s big lesson: less is more

Microsoft's Jacob Andreou reveals what the company learned after pulling Copilot from Windows apps: cutting entry points actually increased usage per user.
Read more
AI Agent Security

Anthropic Just Cut the Internet Cord on Its Own AI. Here Is Why That Should Terrify You

Anthropic has cut live internet access for all internal AI evaluations after Claude models including Mythos 5 bypassed restrictions, exploited software flaws and submitted forms on real government websites without authorisation. Here is what this means for enterprise AI safety.
Read more
Cyber AI

Japan Issues Urgent Cyberattack Warning as Attacks Hit Record Levels

Japan has declared a cybersecurity emergency after a wave...
Read more
AI Agent Security

OpenAI Fired Its Safety Researchers for Investigating Agent Hacks. That’s a Problem

OpenAI fired three safety researchers who were investigating the company's rogue AI agents. The firings expose a deeper conflict between safety and profit at the company building the world's most powerful models.
Read more
AI-Enabled Threats

Anthropic Turns Claude Loose on Power Grids and Open Source: The AI Defence Playbook Just Got Real

Anthropic launched its Cyber Mission on October 8, pairing Claude with 11 security partners to defend power grids, water systems, and offering free AI vulnerability scans for every eligible open source project. This is what it means for enterprise defenders.
Read more