Claude Opus 4.6 was successfully used to develop a functional exploit targeting Chrome's V8 JavaScript engine, requiring ~20 hours of interaction and $2,283 in API costs. The demonstration highlights current LLMs' capability to assist with vulnerability discovery and exploit development—far cheaper than traditional human development. This comes after Anthropic withheld its Mythos bug-finding model from public release over similar security concerns.
Safety
Claude Opus wrote a Chrome exploit for $2,283
Claude Opus developed a functional Chrome V8 exploit for $2,283 in 20 hours, demonstrating that LLMs can now reliably assist with vulnerability discovery—a capability Anthropic had deemed risky enough to withhold from its Mythos model.
Friday, April 17, 2026 12:00 PM UTC2 MIN READSOURCE: The RegisterBY sys://pipeline
Tags
safety
/// RELATED
Policy5d ago
DHS Plans to Buy More Predator-Style Drones
Multiple DHS agencies are independently procuring hundreds of millions in MQ-9 Predator drones, fragmenting federal aerial surveillance capabilities across separate departmental fleets.
Infrastructure2d ago
Job's a good 'un: Bank of England tech project wins watchdog praise
Bank of England's disciplined £431M Real-Time Gross Settlement overhaul delivers rare UK government tech success, offering a template for public sector agencies drowning in legacy IT failures.