←Back to News
Updated April 17, 2026 at 10:00 PMCoinCex editorial review

Anthropic’s Alarming Mythos Findings Replicated With Off-the-Shelf AI, Researchers Say

#Artificial Intelligence

Security researchers used GPT-5.4 and Claude Opus 4.6 in an open-source harness to reproduce Anthropic's Mythos vulnerability findings for under $30 per scan.

How this page was created

This page was derived from source reporting with automated structuring or translation and reviewed for publication by CoinCex.

Original source
Decrypt↗
Anthropic’s Alarming Mythos Findings Replicated With Off-the-Shelf AI, Researchers Say