ACL 2026: Sending AI “~” May Cause It to Delete Your Home Directory
ACL 2026 | 别轻易给AI发「~」,它可能会删掉你的整个主目录
ACL 2026 accepted an LLM safety paper on emoticon semantic confusion. The team tested 6 models with 3,757 cases; average confusion was 38.6%, with over 90% silent failures. The key risk is agent execution, where “ignore emoticons” prompts had limited effect.
Why it matters: A 3,757-sample test across six models found emoji tripped them up 38.6% of the time, and over 90% of those errors passed silently.