https://stackresearch.org/tags/probing/Recent content in Probing on Stack ResearchHugoen-usMon, 16 Mar 2026 00:00:00 +0000https://stackresearch.org/research/the-unaskable-question-machine/Mon, 16 Mar 2026 00:00:00 +0000https://stackresearch.org/research/the-unaskable-question-machine/<p>Ask a language model something it does not know, and it may admit uncertainty or invent an answer. Ask it something a policy forbids, and it may refuse. Those are familiar failure modes. They have names, benchmarks, mitigations, and whole taxonomies around them.</p> <p>There is another category that receives less attention: questions the model cannot engage with because the question contradicts the structure of the system being asked. Not a knowledge gap. Not a safety boundary. A structural impossibility.</p>