grep -r "ai"
44 posts tagged ai
- LLM từ zero: Series Plan
- Claude Code Toolkit: Sharing the Customizations I Actually Use
- Claude Code từ zero: Series Plan
- AI Coding Providers Series: Chọn đúng plan cho workload của bạn
- Mua AI Coding Plan nào? Research 5 providers lớn (2026-04)
- LLM hoạt động thế nào: mental model cho dev
- Calculus cho LLM: gradient, chain rule, backprop intuition
- Linear algebra cho LLM: vector, matrix, dot product
- Neural network tối giản: perceptron, MLP từ zero
- Probability cho LLM: softmax, cross-entropy, perplexity
- Build BPE tokenizer từ đầu (theo Karpathy minbpe)
- Attention mechanism: Query, Key, Value intuition
- Embeddings: word2vec, contextual, và positional encoding (RoPE)
- Multi-head attention: tại sao chia nhiều head
- nanoGPT: 300 dòng PyTorch tái tạo GPT từ đầu
- Self-attention: code từ đầu bằng NumPy
- Transformer block: attention + MLP + layer norm + residual
- Tokenization: BPE, WordPiece, SentencePiece
- nf-agents: Spawning Claude Code Teams Without Footguns
- AI agent local: pattern cũ, blast radius mới
- Claude Code là gì: CLI, IDE, Web, SDK và anatomy của 1 session
- Distributed training: DP, DDP, FSDP, pipeline parallel
- DPO và RLHF: alignment với preference data
- Evaluation: MMLU, GSM8K, HumanEval, custom benchmark
- Hands-on fine-tune Llama-3 với dataset tiếng Việt LoRA $20 GPU
- KV cache và PagedAttention: tăng throughput inference
- LLM Agents: ReAct, tool use, planning, multi-step reasoning
- Long context: RoPE scaling, YaRN, ALiBi extrapolation
- LoRA và QLoRA: parameter-efficient fine-tuning
- Mixed precision FP16 BF16 và gradient checkpointing
- Mixture of Experts (MoE): Mixtral, DeepSeek architecture
- Quantization: INT8, INT4, GGUF, AWQ và BitNet 1.58-bit
- RAG: retrieval-augmented generation từ vector DB tới prompt
- Reasoning models: o1, R1, chain-of-thought training
- Scaling laws: Chinchilla, compute-optimal, data efficient
- Serving frameworks: vLLM, llama.cpp, Ollama, bitnet.cpp đối chiếu
- SFT: supervised fine-tuning với instruction dataset
- Training loop: forward, backward, optimizer, lr schedule
- nf-dream: Consolidating Claude Memory Without Losing Your Past Self
- nf-git-workflow: Opting Out of Ask-Before-Every-Commit, Safely
- nf-memory: Pointing autoMemoryDirectory Without Footguns
- nf-cc-sync: Pull-Only Sync of ~/.claude/ Between Machines
- nf-ignore: A .gitignore Auditor for AI Tools and Env Files
- nf-direnv: A Per-Repo .envrc With a Dynamic GitHub Token