Practice Mode
Quiz Modules
AI concepts · answer, learn, repeat
Agents & Autonomy
Loop Engineering & Agent Harnesses — Advanced
Token cost quadratic growth, prompt caching ROI, context compaction economics, evaluator cascades, convergence detection, proportional budgeting, dynamic fan-out latency, subagent isolation, recovery state machines, trust-but-verify, false-done quantification, dead-letter escalation, harness advantage.
Not started
Start →
Agents & Autonomy
Loop Engineering & Agent Harnesses — Core
Harness architecture, inner agentic loop, context management, turn-based and goal-based loops, time-based loops, evaluation-driven iteration, subagents, dynamic workflows, state persistence, circuit breakers, Claude Agent SDK.
Not started
Start →
Agents & Autonomy
AI Agents in Production — Advanced
Compound error rates, token cost growth, MCP architecture, LangGraph checkpointer trade-offs, Store API memory, interrupt/Command flow, multi-agent patterns (supervisor/swarm/handoff), A2A protocol, planning pattern comparisons, agent evaluation, prompt injection through tools, guardrail layering, trace debugging, deployment security.
Not started
Start →
Agents & Autonomy
AI Agents in Production — Core
Agent loop and ReAct, tool/function calling, MCP, LangGraph state graphs, memory and checkpointing, human-in-the-loop, error handling, multi-agent architectures, A2A, planning, agent evaluation, guardrails, observability.
Not started
Start →
Applied & Production
LLMOps — Advanced
GPU memory math, KV cache sizing, speculative decoding acceptance rates, continuous batching economics, quantization trade-offs, circuit breaker design, semantic cache tuning, OWASP attack chains, cost calculus, capacity planning.
Not started
Start →
Applied & Production
LLMOps — Core
Model serving pipeline, vLLM and PagedAttention, inference optimization, streaming, LLM APIs, routing and fallbacks, caching, input/output guardrails, OWASP LLM Top 10, observability, cost control.
Not started
Start →
Applied & Production
LLM Evaluation & Testing — Advanced
LLM-as-judge biases and debiasing, G-Eval, statistical testing, RAG triad internals, component vs end-to-end eval, agent evaluation, drift detection, A/B testing, red-teaming, eval-harness design.
Not started
Start →
Applied & Production
LLM Evaluation & Testing — Core
Why LLM eval is different, the metric spectrum, classification and generation and retrieval metrics, faithfulness and relevance, golden datasets, LLM-as-a-judge, offline vs online eval, and regression testing.
Not started
Start →
Applied & Production
Prompt Engineering & Context Design — Advanced
Context compression, DSPy optimization, long-context vs RAG, needle-in-a-haystack, ReAct and tree-of-thoughts, constrained decoding, sampling, indirect injection, jailbreaks, and prompt caching.
Not started
Start →
Applied & Production
Prompt Engineering & Context Design — Core
How prompts become token predictions, the context budget, lost-in-the-middle, system prompts, framing, few-shot and chain-of-thought, structured outputs, and prompt injection.
Not started
Start →
Foundations & Architecture
Attention Mechanisms — Advanced
RoPE and ALiBi, long-context extension, KV cache math, MQA/GQA/MLA, prefix caching and PagedAttention, sliding-window and eviction, FlashAttention, and linear attention and SSMs.
Not started
Start →
Foundations & Architecture
Attention Mechanisms — Core
Why attention replaced recurrence, scaled dot-product attention, Q/K/V, multi-head attention, self vs cross attention, causal masking, positional encoding, and the KV cache.
Not started
Start →
Foundations & Architecture
Tokenization — Advanced
BPE optimality and tie-breaking, WordPiece PMI, Unigram EM and Viterbi, subword regularization, byte-to-unicode mapping, glitch tokens, Unicode/homoglyph attacks, character coverage, and tokenizer-free models.
Not started
Start →
Foundations & Architecture
Tokenization — Core
Granularity levels, subword tokenization, the tokenizer pipeline, BPE, byte-level BPE, WordPiece, Unigram, SentencePiece, special tokens, and token counting.
Not started
Start →
Training & Adaptation
LLM Training Pipeline — Advanced
Chinchilla vs Kaplan, compute vs inference optimality, AdamW internals, 3D parallelism, ZeRO stages, stability/loss spikes, MFU, reward modeling, PPO vs DPO, RLAIF, reward hacking.
Not started
Start →
Training & Adaptation
LLM Training Pipeline — Core
Pretraining objective, data curation, scaling laws, Chinchilla, AdamW, LR schedules, mixed precision, distributed training, SFT, RLHF, DPO, training evaluation.
Not started
Start →
RAG
RAG Evaluation & Advanced RAG — Advanced
Faithfulness mechanics, RAGAS/ARES internals, judge bias, RGB, Self-RAG reflection tokens, CRAG, RAPTOR trees, FLARE, contextual retrieval, FiD, long-context trade-offs.
Not started
Start →
RAG
RAG Evaluation & Advanced RAG — Core
Faithfulness, answer/context relevance, retrieval metrics, RAGAS, LLM-as-judge, HyDE, multi-query, Self-RAG, CRAG, RAPTOR, contextual retrieval.
Not started
Start →
RAG
Vector Databases & ANN Search — Advanced
HNSW/IVF/PQ internals, OPQ and ScaNN, scalar/binary quantization + rescoring, filtered ANN, disk-based indexes, MIPS, and distributed sharded search.
Not started
Start →
RAG
Vector Databases & ANN Search — Core
What a vector DB is, ANN vs exact search, HNSW/IVF/PQ indexes, distance metrics, metadata filtering, quantization, and vendor concepts (Pinecone, Qdrant, Milvus, Weaviate, Chroma).
Not started
Start →
RAG
Retrievers & Re-ranking — Advanced
ColBERT/SPLADE internals, DPR/RocketQA training, hard-negative denoising, cross-encoder distillation, RRF tuning, LLM rerankers, lost-in-the-middle, and IR metrics.
Not started
Start →
RAG
Retrievers & Re-ranking — Core
Sparse (BM25) vs dense retrieval, hybrid search and RRF, bi- vs cross-encoders, ColBERT late interaction, SPLADE, query expansion (HyDE), and retrieval metrics.
Not started
Start →
Foundations & Architecture
Embeddings — Advanced
Contrastive-loss internals, anisotropy and whitening, hard-negative mining (ANCE), DPR/ColBERT late interaction, Matryoshka, decoder embeddings (LLM2Vec), and evaluation trade-offs.
Not started
Start →
Foundations & Architecture
Embeddings — Core
Dense vectors, word2vec/GloVe/fastText, static vs contextual, sentence embeddings and SBERT, bi- vs cross-encoders, similarity metrics, contrastive learning, and Matryoshka.
Not started
Start →
Efficiency & Serving
Inference Optimization — Advanced
Roofline reasoning, FlashAttention internals, chunked prefill and disaggregation, PagedAttention internals, speculative-decoding acceptance, KV reduction, and tensor-parallel serving.
Not started
Start →
Efficiency & Serving
Inference Optimization — Core
Prefill vs decode, KV cache, MQA/GQA, continuous batching, PagedAttention/vLLM, FlashAttention, speculative decoding, and serving metrics.
Not started
Start →
Efficiency & Serving
Quantization & Compression — Advanced
Method internals and trade-offs: GPTQ/AWQ/SmoothQuant/LLM.int8, NF4 and double quant, FP8, SparseGPT vs Wanda, KV-cache quant, extreme low-bit, distillation objectives.
Not started
Start →
Efficiency & Serving
Quantization & Compression — Core
Numeric formats, scale and zero-point, PTQ vs QAT, weight vs activation quantization, LLM.int8/GPTQ/AWQ/NF4, distillation, and pruning.
Not started
Start →
Training & Adaptation
Fine-tuning & PEFT — Core
Full fine-tuning vs parameter-efficient methods: LoRA, QLoRA, adapters, prefix/prompt/P-tuning, freezing, rank and alpha, adapter merging, and when to fine-tune.
Not started
Start →
Foundations & Architecture
Transformer Architecture — Core
Self-attention, Q/K/V, multi-head attention, positional encoding, residuals, layer norm, the FFN, embeddings, and the encoder/decoder stacks.
Not started
Start →
Foundations & Architecture
Transformer Architecture — Advanced
Attention complexity and FlashAttention, MHA vs MQA vs GQA, sparse and sliding-window attention, KV-cache math, Pre/Post-Norm and DeepNorm, attention sinks, head redundancy, and training-stability trade-offs.
Not started
Start →
RAG
RAG Fundamentals — Core
The retrieve-then-generate pipeline: loading, chunking, embedding, retrieval, reranking, grounded generation, evaluation, hybrid search, and RAG vs fine-tuning.
Not started
Start →
RAG
RAG Fundamentals — Advanced
Chunking and embedding trade-offs, hybrid fusion (RRF), query transforms (HyDE, multi-query), retrieval metrics (MRR, nDCG, context precision/recall), faithfulness vs relevancy, reranking cost, and failure diagnosis.
Not started
Start →
Training & Adaptation
Fine-tuning & PEFT — Advanced
LoRA math and rank/alpha, QLoRA internals (NF4, double quant, paged optimizers), DoRA, AdaLoRA, LoRA+, multi-adapter serving, quantization interplay, and forgetting trade-offs.
Not started
Start →
About Nybble™
The AI space moves fast.
Nybble™ is how you keep up — and stay sharp.
What happened. In two minutes.
The AI news cycle moves at a pace no one can keep up with. Snack distills what launched, what shipped, and what matters — every day, without the filler.
Go to SnackThe concepts behind the headlines.
News tells you what. Stack tells you why and how. From RAG architectures to agentic evals, these are the ideas that will shape what you build next.
Go to StackProve you actually get it.
Reading about LangChain is not the same as knowing it. Hack challenges you with production-grade questions, then shows you the references that make the answer stick.
Go to Hack