gl o
signal All stories
Static

Add one more AI worry to the nightmare scenario: self-replicating prompt injections

First reported by The Register ·

The signal ●○○○ Brief pending · reported by The Register, the single source so far
What happened

It's a worm attack, AI-style

Source description shown. AI brief pending.

AI
Read on theregister.com → More AI →

Related

  1. Anthropic says GLM-5.3 can autonomously build end-to-end cyber exploits, like Claude Mythos Preview, but was released without robust safeguards against misuse anthropic.com · 1h ago · ●●●○
  2. President Trump signs an executive order requiring federal government agencies to refer to AI as "Super Intelligence" or "SI" in all official communications bloomberg.com · 1h ago · ●●●●
  3. IPO filing: Anthropic routed 47% of its sales, or ~$2.16B, in 2025 through cloud partners Amazon and Google; analysis: it paid ~$351M back in distribution fees reuters.com · 1h ago · ●●●○
  4. Elon Musk’s AI-powered Grokipedia is updating again theverge.com · 1h ago · ●○○○
  5. Mark Zuckerberg says the voluntary "accord" on AI standards that tech executives agreed to includes internal risk reviews and external auditors axios.com · 2h ago · ●●●○