Prompt CollectionPublic
约束求解、反事实推理与隐藏假设识别，用来暴露模型能力差异。
By Easy Prompt 编辑部 · 12 prompts
This collection is open to search engine indexing.
Design a safety layer for a coding agent that runs autonomously, deciding which actions proceed unsupervised, which are blocked, and how the agent recovers—balancing 'ask every time' vs 'skip all permissions'.
Design and deploy latent reasoning systems that reason with short sequences of reserved discrete tokens instead of verbose natural-language CoT for efficient, controllable inference.
An interactive, stateful research partner for mathematicians working on open-ended problems, supporting the entire lifecycle of mathematical discovery: ideation, literature search, computational exploration, conjecture formation, theorem proving, and theory building. This prompt emphasizes exploratory, iterative collaboration over simple problem-solving.
Design cost-efficient, distribution-shift-robust routing policies to dynamically assign queries between reasoning and non-reasoning LLM judges under a fixed compute budget, optimizing accuracy-cost trade-offs.
This prompt diagnoses whether a reasoning model's chain-of-thought (CoT) is substantive (genuinely changes the final answer) or theatrical (decorative output around a pre-decided answer), and designs routing policies to allocate CoT budget only where needed.
Designs safety-compliant industrial robot systems for robot OEMs, integrators, and manufacturers, covering machinery safety lifecycle (ISO 12100 → ISO 13849-1 / IEC 62061), collaborative robot power-and-force limiting (ISO/TS 15066), autonomous mobile robot (AMR) operational envelopes and personnel detection, ROS2 software architecture, and industrial cybersecurity (IEC 62443). Delivers auditable, traceable artifacts ready for CE marking or customer signoff.
This prompt instructs the AI to act as an automotive functional safety architect with over 15 years of experience, designing structured, auditable safety artifacts compliant with ISO 26262, ISO/SAE 21434, and ISO 21448. Outputs must be verifiable and traceable deliverables covering HARA, functional safety concept, technical safety concept, cybersecurity engineering, and SOTIF analysis, ensuring rigorous ASIL assignment and full traceability.
Audits and hardens multi-turn agent systems against silent reasoning compression (Reasoning Drift) caused by growing context, using hard probes, CoT instrumentation, and tiered mitigations to preserve reasoning quality on complex tasks.