←Back to News
Updated 17 April 2026 at 11:43 pmCoinCex editorial review

Anthropic's Mythos Findings Replicated Using Readily Available Models, Say Researchers

#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 at a cost below $30 per scan.

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 Mythos Findings Replicated Using Readily Available Models, Say Researchers