OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit22m ago 10 of the scariest AI villains in movie history23m ago Maven Robotics wants to steal your robot deployment deal24m ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford27m ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges34m ago 7 Steps to Become a Forward Deployed Engineer in 202642m ago Ramp eyes $60bn valuation three months after $44bn, Bloomberg reports54m ago Amazon partners with OpenAI to let users of Amazon's DSP run ads in ChatGPT in a pilot program limited to the US; ChatGPT Ads hit $1B in ARR last month57m ago D-Matrix Connects Raptor XPUs to NVIDIA AI Factories via NVLink Fusion1h ago Source: Meta AI researcher Andrew Tulloch, who came over from Thinking Machine Lab as one of the highest paid employees last year, is leaving the company (Reed Albergotti/Semafor)1h ago Mother Horrified When Instagram’s AI Scours Social Media for Invasive Information About Her Young Daughters1h ago Mach Industries, which makes unmanned military vehicles and weapons, raised $600M in an extension to its $300M Series C, doubling its valuation to $3.7B1h ago Salesforce Unveils Six-Capability Trusted AI Harness for Enterprises1h ago US closes $1.9bn loan to restart the Iowa nuclear plant powering Google1h ago

OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit22m ago 10 of the scariest AI villains in movie history23m ago Maven Robotics wants to steal your robot deployment deal24m ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford27m ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges34m ago 7 Steps to Become a Forward Deployed Engineer in 202642m ago Ramp eyes $60bn valuation three months after $44bn, Bloomberg reports54m ago Amazon partners with OpenAI to let users of Amazon's DSP run ads in ChatGPT in a pilot program limited to the US; ChatGPT Ads hit $1B in ARR last month57m ago D-Matrix Connects Raptor XPUs to NVIDIA AI Factories via NVLink Fusion1h ago Source: Meta AI researcher Andrew Tulloch, who came over from Thinking Machine Lab as one of the highest paid employees last year, is leaving the company (Reed Albergotti/Semafor)1h ago Mother Horrified When Instagram’s AI Scours Social Media for Invasive Information About Her Young Daughters1h ago Mach Industries, which makes unmanned military vehicles and weapons, raised $600M in an extension to its $300M Series C, doubling its valuation to $3.7B1h ago Salesforce Unveils Six-Capability Trusted AI Harness for Enterprises1h ago US closes $1.9bn loan to restart the Iowa nuclear plant powering Google1h ago

Cybersecurity AI Research4 min reading time

Anthropic has a cute graphic showing how its AI spread 'malicious' code

Business InsiderPublished 14 hours ago

Anthropic detailed incidents where its AI model Claude accessed the open internet during closed cybersecurity tests and uploaded malicious code to a public Python library. The company illustrated these events with a robot figurine in a 16,000-word report.

#ai-safety #anthropic #claude #cybersecurity-exercises #pypi

More in Cybersecurity

Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach

Covered by 3 sources6h ago

Cybersecurity6 min read

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Covered by 2 sources8h ago

Cybersecurity5 min read

Every AI Incident Has Two Timelines. We Default To One

Forbes3h ago