Browse and take tests to sharpen your skills
Advanced prompting: eval harnesses, adversarial robustness, multi-step agents, cost/latency tradeoffs, grounding quality, and production governance. Mix of single-answer and multiple-answer items; multi-select questions ask you to select every correct statement.
Intermediate prompting: chain-of-thought, structured outputs, evaluation, RAG vs prompting, context limits, and injection awareness. Mix of single-answer and multiple-answer items; multi-select questions ask you to select every correct statement.
Foundations of prompting LLMs: clarity, roles, few-shot examples, output format, and basic safety. Mix of single-answer and multiple-answer items; multi-select questions ask you to select every correct statement.
RAG failure modes, agents/tools, LLM-as-judge caveats, jailbreaks, RAG vs fine-tune, KV cache, semantic cache, ACL retrieval, speculative decoding, and SLOs.
RAG chunking/retrieval, prompt injection, tools, structured outputs, evals, hybrid search, cost/latency, memory, guardrails, and faithfulness.
LLM basics: tokens, temperature, context window, hallucinations, system prompts, RAG/embeddings intro, few-shot, rate limits, and safety.
Bias–variance, calibration, interpretability caveats, imbalance metrics, deep learning training dynamics, transfer/domain shift, causality limits, nested CV, and drift.
Regularization, ROC/F1, imbalance, scaling, encodings, ensembles, leakage, early stopping, losses, softmax, embeddings, and tuning discipline.
Supervised vs unsupervised, splits, overfitting, labels, classification vs regression, metrics basics, loss, gradient descent, and cross-validation.
Tell us which topic or difficulty level you need — no account required.