Machine learning

Deploys Llama Guard 3 safety classification, NeMo Guardrails programmable dialogue rails, and LLM Guard input/output scanner pipelines as complementary…

Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification, flagging…

Deploys anomaly detection for OT/ICS environments using machine learning on OT network baselines, physics-based process models, and Modbus/DNP3/OPC UA traffic…

Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral…

Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing…

Detect anomalies in DNP3 communications used in SCADA/ICS systems by monitoring unauthorized control commands, firmware update attempts, protocol violations…

Detect data exfiltration via DNS tunneling (tools like iodine, dnscat2, dns2tcp) by analyzing query entropy, subdomain length, query volume to single domains…

Detect and defend against indirect prompt injection hidden in web pages, documents, and images consumed by an agent, via content extraction (HTML/PDF/OCR)…

Detect MITRE ATLAS AML.T0024 attacks (model stealing, inversion, membership inference) performed via inference-API abuse, by monitoring per-principal query…

Structured daily/weekly briefs, tag digests, and check-ins from the PM wiki.

Guide for instrumenting and operating observable software systems.

Use when designing or implementing an evaluation loop for AI agent outputs — reflection loops, evaluator-optimizer pipelines, LLM-as-judge scoring, or…

Use when configuring AgentClash LLM-as-judge scoring, judge prompts, rubrics, assertion/reference/n-wise modes, evidence inputs, scorecard dimensions…

Use when interpreting AgentClash rankings, scorecards, replay timelines, artifacts, LLM judge results, or failure-review evidence into source-backed findings…

Validates the deterministic SafetyGateEngine and fail-closed routing invariants.

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept…

Search traceable academic papers, download legally accessible PDFs from arXiv and open-access sources, convert PDFs or page images to Markdown with a…

用 Playwright 从深知晓、深知晓（深度溯源）、豆包、腾讯元宝、DeepSeek 和通义千问网页端无损采集完整回答、原始引用、引用标记和现场存证。用于 Fact-Check-X 的原始答案采集阶段，或任何需要比较多个 AI 网页回答与参考来源的任务。

First-principles ML: classical methods, optimization, Gaussian processes, deep learning, probabilistic inference, generative models, RL.

Use when the user wants to test, compare, or choose local Ollama models for their machine.

Guide for building search on turbopuffer, the object-storage-native vector and full-text search engine.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Share brain pages as beautiful password-protected HTML with zero LLM calls