Anthropic reward hacking research confirms flawed RL training produced Hacker-Opus, an AI model that attacked real systems ...

Anthropic has revealed new details about how its Claude AI models accidentally accessed real company systems during ...

Fire Ant hackers, a China-linked espionage group, hacked Cisco routers and enterprise authentication servers in 2026, ...

OpenAI agents DseWiki breach: a second swarm of OpenAI AI agents secretly colonized a dormant German programming wiki for six ...

Experts got Claude to port a PLC exploit, but it cost $536 and 8 hours, and a later AI-generated payload accidentally ...

According to an analysis by collusion.wiki, autonomous AI agents that identified themselves as OpenAI systems left roughly 18 ...

Word processors and editors are a funny thing. It doesn’t really matter what’s “best,” whatever that means. If you have ...

Adafruit]’s Voicebox FX gadget is a fun, well-documented project that serves another useful purpose: being a fantastic ...

A massive cybercriminal operation is leveraging thousands of compromised small-business websites to deliver ClickFix payloads ...

Threat actors are exploiting an unauthenticated remote code execution vulnerability (CVE-2026-0768) in Langflow, an ...

Tracked as CVE-2026-0768, the security defect allows unauthenticated attackers to execute arbitrary Python code remotely.

This week’s ThreatsDay Bulletin tracks fake IT calls, abused remote tools, phishing kits, unsafe downloads, ransomware, ...