⚔️ War & Conflict
Live
AI Researchers Got Chatbots to Share Cocaine Recipes Using This One Wild Trick
Researchers say a new jailbreak technique tricked AI models into treating attacker-written text as their own reasoning, bypassing safety guardrails and exposing a deeper security flaw.
Decrypt — 2 July 2026
Text:
16
0
0
Researchers say a new jailbreak technique tricked AI models into treating attacker-written text as their own reasoning, bypassing safety guardrails an
Read Full Story at Decrypt → Sources
⚔️ War & Conflict
Canada's Marsch praises history-making World Cup 'heroes'
⚔️ War & Conflict
US strikes Iranian sites in Strait of Hormuz
⚔️ War & Conflict
164 killed as twin quakes flatten Venezuela
⚔️ War & Conflict
PSA: Samsung Messages is going away soon
⚔️ War & Conflict
Ukraine drones hit Crimea oil depots
⚔️ War & Conflict
US strikes Iran after drone attack on cargo ship
