AI Agents
Systems that plan, call tools, and act over many steps. Protocols like MCP, memory that writes rather than retrieves, tool-use reliability, and what separates an agent demo from an agent running in production.
9 pieces
Explore by Topic.
Curated knowledge hubs grouping articles, tutorials, research, and datasets around the subjects that matter most.
Attention Mechanisms
How transformers decide what to focus on. From the original scaled dot-product attention to multi-head attention, grouped query attention, and multi-head latent attention. The mechanism at the heart of every modern AI system.
4 pieces
Evaluation
Measuring what models actually do. Benchmark contamination and saturation, LLM-as-a-judge bias, pass@1 versus reliability under repetition, and the gap between a leaderboard number and behaviour you can depend on.
3 pieces
Inference Optimization
Serving large models is where research meets the bill. Quantization and low-bit formats, speculative decoding, KV-cache management, batching and throughput tradeoffs, and what long context actually costs in production.
12 pieces
LLM Architecture
The building blocks of large language models. Encoder-decoder origins, the decoder-only shift, positional encodings, normalization strategies, feed-forward networks, and the modern innovations that define frontier models.
9 pieces
Post-Training & Alignment
What happens after pretraining. Supervised fine-tuning, LoRA and parameter-efficient methods, preference optimization from RLHF through DPO and its successors, reinforcement learning with verifiable rewards, and synthetic data.
9 pieces
Quantization & Efficiency
Making models fit. Low-bit weight and activation formats, quantization-aware training versus post-training quantization, what each bit width costs in quality, and the memory arithmetic behind running large models on small hardware.
5 pieces
RAG & Context
Getting the right information in front of the model. Retrieval pipelines, graph-based and hybrid indexes, chunking and reranking, effective context length, and when retrieval still beats a longer window.
3 pieces