Analysis · curated 25 Aug 2026

AI: ‘Forever Problems’ like Prompt Injections still being ‘Solved’. AI-RTZ #1167

Coverage timeline

25 Aug 2026substack.com

Single-source analysis — first reported, latest, and curated coincide.

Why it matters

Prompt injection remains an unsolved, structural weakness in LLM-based agents, and this analysis reminds defenders that longer-running autonomous agents expand the attack surface rather than close it.

An essay on the 'AI Reset to Zero' Substack argues that prompt injection and hallucinations are 'forever problems' intrinsic to probabilistic AI models, not bugs that labs can permanently 'solve,' and that the risk grows as AI agents run for days or weeks, widening the window an attacker has to inject instructions. The piece cites Anthropic's Boris Cherny and references Simon Willison's 'lethal trifecta' framing (private data, untrusted content, and external communication) as the core mechanism behind agentic data exfiltration.