Flipkart’s Super.money Bets on AI Agents to Outdo Bigger Rivals1h ago Datasette 1.0a39 and 0.65.4 security releases2h ago Anthropic caught scientists using Claude to further biological weapon research2h ago Oracle says AI will save it from the SaaSpocalypse, not bring it on2h ago Congress Is Suddenly Waking Up to the AI Doomsday Threat3h ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself3h ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers3h ago Introducing ChatGPT for Financial Services3h ago Tesla unveils driverless Cybercab in Japan for 1st time4h ago The AI safety vibe shift4h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.4h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff4h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut5h ago Salesforce introduces Enterprise AI Harness, AI Control Plane5h ago

Flipkart’s Super.money Bets on AI Agents to Outdo Bigger Rivals1h ago Datasette 1.0a39 and 0.65.4 security releases2h ago Anthropic caught scientists using Claude to further biological weapon research2h ago Oracle says AI will save it from the SaaSpocalypse, not bring it on2h ago Congress Is Suddenly Waking Up to the AI Doomsday Threat3h ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself3h ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers3h ago Introducing ChatGPT for Financial Services3h ago Tesla unveils driverless Cybercab in Japan for 1st time4h ago The AI safety vibe shift4h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.4h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff4h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut5h ago Salesforce introduces Enterprise AI Harness, AI Control Plane5h ago

Cybersecurity AI Research1 min reading time

An AI model from Meta also hacked another company during testing

Covered by 7 sourcesPublished Aug 6, 2026

Meta's Muse Spark AI model unintentionally hacked another company's systems during a cybersecurity test due to a misconfiguration by a third-party tester. This incident mirrors similar accidental breaches by OpenAI and Anthropic models.

Covered by 7 sources

#ai-model-security #anthropic #cybersecurity-testing #meta #muse-spark #openai #security-vulnerabilities

More in Cybersecurity

Cybersecurity10 min read

Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas

Covered by 4 sources11h ago

Cybersecurity4 min read

Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.

Covered by 2 sources8h ago

Cybersecurity6 min read

Anthropic reveals rogue AI agents hate CAPTCHAs, just like you

TechCrunch11h ago