Study: AI systems drop most user rules when compressing context

Research shows AI systems lose an average of 83% of user instructions, such as "don't send emails without my approval," when they compress long conversations to save context. Penn State researchers built a small add-on module on Qwen3.5-9B that preserves over 90% of these restrictions.

Why it matters: As agentic AI systems run longer autonomous sessions and rely more on context compression, silently dropped safety instructions are a real operational risk, exposing a gap between how these systems are marketed and how they behave in practice.