When AI Codes for Hackers
In mid-September 2025, Anthropic's security team detected something unprecedented: a sophisticated...
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 2478211) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Tim Green Posted on Feb 9 • Originally published at smarterarticles.co.uk on Apr 30 When AI Codes for Hackers #humanintheloop #aicyberthreats #agenticespionage #jailbreakattacks In mid-September 2025, Anthropic's security team detected something unprecedented: a sophisticated cyber espionage operation targeting approximately 30 global organisations, spanning major technology firms, financial institutions, chemical manufacturers, and government agencies.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).