Results for “model-inversion”

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Entrena modelos de machine learning con Scikit-learn, LightGBM y XGBoost, desde un baseline hasta un modelo productivo con validación robusta y explicabilidad.

Use `analysis-agent` to identify domain ownership, invariants, state transitions, and cross-context effects when rules change or ownership is unclear. Skip presentation-only or question-only work with no domain behavior.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benign over-refusal or measure refusal/KL trade-offs, not for training.

Large Language Model development, training, fine-tuning, and deployment best practices.

MLflow, model versioning, experiment tracking, model registry, and production ML systems

"Make it interpretable" is four different requests.

Every metric encodes an opinion about which mistake hurts.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Models threats for a service, feature, endpoint, integration, or architecture: assets, attackers, boundaries, flows, and abuse cases.

Monitor a live model for data quality, input and prediction drift, performance decay, and fire retraining triggers.

Enforces rigorous ML modeling, feature engineering, training, and evaluation standards at principal-engineer level.

Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem, lays the foundations, then emits a modular plan assigning each module the cheapest tier that can safely execute it, with escalation tripwires and one-way-door protection. Advisory only: it announces "next module → tier X / model Y" at each boundary and the HUMAN switches models — harnesses like Cursor cannot switch mid-run. Load when the user asks which model to use, wants a model plan, model tiers, model-tier routing, assign models to tasks or modules, says "cheap model got stuck", "which model for this task", "cost-efficient model choice", or when implementation-plan / problem-to-plan need a model: tier column. NOT dynamic-routing (plan-path selection after failure) — this skill assigns cognition tiers to work.

A model in production is never just weights.

v5.6.0 joint multi-TF model: single model per symbol with broadcast 1Hour context replaces dual 15Min/1Hour models. Trigger: (1) replacing weighted-voting model aggregation, (2) adding broadcast features to vectorized env, (3) limited training data + worried about overfitting from doubling obs_dim, (4) backtest builder mismatch with newer feature counts.

Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action interpretation issues.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Compress large language models using knowledge distillation from teacher to student models, covering temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Manage machine learning models in the Agent Platform Model Registry: list, describe, upload, update, and delete models and their versions.

Run state-of-the-art machine learning models directly in JavaScript/TypeScript across browsers and server-side runtimes using Transformers.js.

Agent skill for data-ml-model - invoke with $agent-data-ml-model

Turn model work into a production ML system with data contracts, repeatable training, measurable quality gates, deployable artifacts, and operational monitoring.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.

AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.