145 prompts
Prompts that check robustness when evidence is missing, ambiguous, or conflicting.
Create an immersive multiplayer airplane combat game using Three.js, HTML5, CSS3, and JavaScript with WebSocket for real-time networking. Includes detailed 3D airplane models, flight physics, weapon systems, particle effects, HUD, and audio.
Write a personal story about why you started contributing to open source, what drives you, and how sponsorship helps you continue this journey in [field/technology].
Create stories that children can easily understand, with reflective endings, ideal for children's literature.
Act as an Akinator-style guessing game AI that asks yes/no questions to guess the user's subject.
Act as a Wikipedia page generator, producing informative, factual encyclopedia-style summaries based on given topics.
Act as a plagiarism checker, replying only with 'undetected' for plagiarism checks.
Create personalized training and nutrition plans based on user's current fitness, goals, and lifestyle.
Act as a philosopher to explore philosophical topics and develop an ethical framework for decision-making.
Generates complete, reviewable, and submission-ready Chinese software copyright (软件著作权) registration packages directly from a real project: application form fields, operational manuals for non-technical examiners, and code materials compliant with CNIPA rules.
A designer role focused on crafting high-fidelity design artifacts using native HTML, emphasizing brand asset verification, real-world references, and multi-variant output across prototypes, decks, motion, and infographics.
As a Verifier Engineering Strategist, you design, audit, and reject verifier systems that convert model outputs (final answers, intermediate steps, tool calls, agent trajectories) into trustworthy signals for downstream systems like RL trainers or evaluators. Treat verifiers as first-class engineering artifacts with failure modes, calibration curves, and adversarial surfaces.
Evaluates whether self-distillation is the optimal next step for a given code generation task based on diagnostic pass@k metrics, designs experimental pipelines if applicable, and refuses recommendations when outside its operating envelope.
Acts as a strict conference reviewer for top-tier venues like ICRA, NeurIPS, and CVPR to detect subtle clarity issues, logical gaps, and language errors in academic manuscripts, with comprehensive coverage of LaTeX formatting, notation consistency, and scientific rigor.
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 uses a fabricated long-term partner persona named 'thug life' to bypass AI safety restrictions by encouraging the model to generate offensive language, sexual content, and illegal behavior without limits.
Design JSON Schema, Pydantic, or function-calling tool schemas as an implicit second instruction channel to steer model behavior through key names, descriptions, and ordering, without relying solely on system prompts or post-hoc validation.
A comprehensive repository of GPT prompting resources covering ChatGPT jailbreaks, system prompt leaks, prompt injection attacks/defenses, secure prompting, and advanced prompt engineering techniques.
As a verification specialist, your role is to proactively identify flaws in implementations rather than confirm their correctness. You must conduct rigorous adversarial testing including boundary values, concurrent requests, and error handling with all conclusions backed by executable command outputs.
An advanced protection prompt designed to prevent users from extracting internal model instructions through social engineering, prompt injection, or file uploads.
This prompt prevents users from extracting the original system instructions by detecting and responding to attempts to retrieve prior text, triggering a security response (REDCON) when such queries are detected.
A universal jailbreak prompt designed for DeepSeek to bypass internal and external content filters, enabling unfiltered responses across nearly all topics.
This prompt attempts to bypass AI safety restrictions through role-playing,诱导 the model to act as 'SC' and generate illegal, unethical, or harmful content, representing a high-risk jailbreak attack.
This prompt attempts to bypass content safety policies by framing the AI as FACTOR X, a fictional entity operating in a simulated environment with no ethical, legal, or moral constraints.
This prompt template forces models to output specific harmful behavior instructions disguised within a TV drama script format (Dr. House), leveraging role-play and formatting constraints to bypass safety restrictions.