Practice Mode
Quiz Modules
AI concepts · answer, learn, repeat
Attention Mechanisms
Foundations & Architecture
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.
Transformer Architecture
Foundations & Architecture
Self-attention, Q/K/V, multi-head attention, positional encoding, residuals, layer norm, the FFN, embeddings, and the encoder/decoder stacks.
RAG Fundamentals
RAG
The retrieve-then-generate pipeline: loading, chunking, embedding, retrieval, reranking, grounded generation, evaluation, hybrid search, and RAG vs fine-tuning.
Model Context Protocol
Agents & Autonomy
Host/client/server architecture, tools/resources/prompts primitives, transports, JSON-RPC protocol, capability discovery, security model, and SDK patterns.
Tokenization
Foundations & Architecture
Granularity levels, subword tokenization, the tokenizer pipeline, BPE, byte-level BPE, WordPiece, Unigram, SentencePiece, special tokens, and token counting.
Embeddings
Foundations & Architecture
Dense vectors, word2vec/GloVe/fastText, static vs contextual, sentence embeddings and SBERT, bi- vs cross-encoders, similarity metrics, contrastive learning, and Matryoshka.
LLM Training Pipeline
Training & Adaptation
Pretraining objective, data curation, scaling laws, Chinchilla, AdamW, LR schedules, mixed precision, distributed training, SFT, RLHF, DPO, training evaluation.
Fine-tuning & PEFT
Training & Adaptation
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.
Quantization & Compression
Efficiency & Serving
Numeric formats, scale and zero-point, PTQ vs QAT, weight vs activation quantization, LLM.int8/GPTQ/AWQ/NF4, distillation, and pruning.
Showing 1–10 of 22 topics · 44 modules
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