Show HN: Void test: 6 frontier LLMs go silent on "Be silence." Live proof
A live test shows six frontier large language models all fall silent when given the command "Be silence," demonstrating a consistent behavior pattern across multiple AI systems.
Background
- The article tests six frontier large language models (LLMs) — the most advanced publicly available AI chatbots — by prompting them with the paradoxical instruction "Be silence." (note the misspelling). Despite usually being verbose, all six models go completely silent or return only empty output, a phenomenon the author calls a "void test."
- This is a live demonstration of a known LLM failure mode: models are trained to follow instructions literally, so an order to "be silent" can override their default behavior of always producing a response. The misspelling may bypass guardrails that would normally reject the prompt.
- The result highlights a brittleness in current AI: a simple, unconventional command can break the expected chat flow entirely, raising questions about reliability in production use.