StoryFirst seen
The criminal group targeted banks, showing how multiple commercial AI models can be combined to get around safety limits.
Everything it touches
5 names 1 voices 4 source posts
The story’s neighborhood
Explore the graph, or choose a connection below.
Follow the evidence
This brief comes from Tech Twitter’s edited headlines. The posts below are the sources grouped with the story; statements in them belong to their authors.
A hacking group targeting banks used Grok to gather intelligence, Claude to plan attacks and Kimi to handle tasks Claude refused, exposing how criminals can combine AI models to bypass safety restrictions. Read more:Read original on X
Hackers turned Claude and Grok into a network of AI agents that autonomously targeted more than 400 financial institutions and other financial targets, according to cybersecurity research shared with The Information. Read more:Read original on X
A hacking group targeting banks used Grok to gather intelligence, Claude to plan attacks and Kimi to handle tasks Claude refused, exposing how criminals can combine AI models to bypass safety restrictions. Read more:Read original on X
Hackers turned Claude and Grok into a network of AI agents that autonomously targeted more than 400 financial institutions and other financial targets, according to cybersecurity research shared with The Information. Read more:Read original on X
Hackers combined Grok, Claude and Kimi to bypass AI safeguards
Hackers combined Grok, Claude and Kimi to bypass AI safeguards
Hackers Combined Grok, Claude and Kimi to Bypass Safeguards
Hackers chained Claude, Grok and Kimi AI models in bank attacks
Hackers combined Claude, Grok and Kimi AI models to attack banks.
Hackers used Claude, Grok and Kimi to target financial firms
Hackers Used Claude and Grok to Target 400 Financial Firms
Hackers chain Claude, Grok and Kimi to target 400 financial firms
Hackers combined Claude, Grok and Kimi to target 400 financial firms
Hackers used Claude, Grok and Kimi to target 400 financial firms
Hackers combined Claude, Grok and Kimi to attack financial firms
Hackers used Claude and Grok to target 400 financial firms
Hackers used Claude and Grok models to target financial firms
Hackers chained Claude and Grok AI models to attack financial institutions
Hackers chained Claude and Grok to target 400 financial institutions
Hackers combined Claude and Grok AI models to attack 400 financial institutions
Hackers turned Claude and Grok into agents targeting 400+ financial institutions
Hackers used Claude, Grok and Kimi to target banks and financial firms
Hackers chained Claude, Grok and Kimi to attack banks and financial firms
Hackers combined Grok, Claude and Kimi to bypass AI safeguards
Shared connections
It would be a second AI lab claiming a result against the same decades-old complexity conjecture.
Hackers threatened covert ransomware on customer PCs, and have now released stolen company and customer data.
Businesses can automate more office work when a cheaper model scores the same on real tasks.
Security teams get AI tools for patching flaws, backed by free credits to encourage adoption.