Results for “safety”

Audits medical LLM benchmarks across five lifecycle phases using 46 medically tailored criteria to assess clinical relevance, data integrity, safety-critical capabilities, validity, and governance.

Enforces bulk-safety rules, sharing model requirements, CRUD/FLS security, SOQL injection prevention, PNB test coverage, and modern Apex idioms for Salesforce development.

Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Train AI models to be harmless through self-critique and AI feedback using a set of constitutional principles, without requiring human labels for harmful outputs.

Integrate Claude agents into training and live trading (v3.0). Trigger when: (1) setting up multi-agent training, (2) adding agent consultation to live trading, (3) configuring orchestrator, (4) understanding agent roles and safety mechanisms.

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution on local Docker, Slurm HPC, or cloud platforms.

Route AI agent engineering prompts to architecture, orchestration, evaluation, safety, debugging, context, prompt, MCP, persona, local AI, and Compound Engineering skills. Use when prompts mention agents, agent harnesses, agentic workflows, orchestration, evals, context management, MCP servers, or compound engineering.

Evaluates Base ERC-20 tokens by contract address, returning a 0-100 score across five criteria, launch protocol classification, security flags, and a narrative interpretation.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Audit installed SKILL.md files and companion scripts for shell injection, secret exfiltration, path traversal, prompt-override payloads, destructive commands, and obfuscation. Integrates with Bankr Safety Scores and produces delta reports against prior scans.

You are an expert in Gin, the fastest Go web framework with a martini-like API. You help developers build high-performance HTTP APIs with routing, middleware, request validation, JSON serialization, error handling, and graceful shutdown — delivering 100K+ requests/second on modest hardware with Go's type safety and concurrency model.

Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.

Implements age-gating mechanisms for online services to restrict access based on user age. Covers hard gates versus soft gates, neutral age prompts, re-verification triggers, circumvention prevention, and regulatory requirements under GDPR, COPPA, UK Online Safety Act, and DSA. Keywords: age gate, age restriction, neutral prompt, children, online services, access control.

Skilled agent architecture replacing multi-agent system for RL training. Trigger when: (1) planning agent-guided training, (2) implementing tool-augmented LLM consultations, (3) comparing skilled vs multi-agent approaches, (4) designing simulate-verify loops for training, (5) implementing prompt evolution / learnable parameters, (6) understanding Claude Agent SDK integration in training, (7) debugging SkilledTrainer consultations or tool calls, (8) configuring agent safety bounds for training actions.

Orchestrator for the eval-output skill suite — evaluate LLM and agent outputs for quality, accuracy, helpfulness, and safety using structured rubrics and LLM-as-judge techniques. Load when the user says "evaluate this output", "score this response", "run an eval", "LLM as judge", "evaluate agent output", "how good is this response", "rate this answer", "eval this", or provides an LLM output that should be assessed for quality. Single entry point for all output evaluation workflows.

Use to audit a customer-facing support bot or AI agent for harm rather than for volume — manipulation and prompt-injection attempts, customers stranded without a human, fabricated answers, and unsafe commitments or disclosures. Trigger for "are people trying to jailbreak our bot", "show me attempts to manipulate the assistant", "is our bot giving wrong answers", "customers stuck with the bot and never got a human", or reviewing an AI agent before or after launch.