Blog
Latest articles
10 min readDeploying ML Models on Cloudflare Workers and WebAssembly (Wasm)
Learn to compile model pipelines down to Wasm binaries to execute real-time, zero-cold-start inference at the network edge.
9 min readGraph RAG: Combining Vector Databases with Knowledge Graphs
Traditional retrieval often misses complex relationships. Learn how to map structural nodes alongside vector indices to enhance RAG systems.
8 min readContext Window in LLMs Explained: Why It Matters More Than You Think
A context window is the total text an LLM can see at once. GPT-4o holds 128k tokens, Claude 200k, Gemini 1M. Here is what that means for your work.
9 min readMMLU Explained: What the 57-Subject LLM Benchmark Actually Tests
MMLU covers 57 academic subjects with 15,908 multiple-choice questions from elementary to professional level, and remains one of the most widely cited LLM benchmarks despite significant criticisms.
7 min readEffect-TS: Handle Errors and Dependencies With Full Type Safety in TypeScript
Effect-TS tracks errors and dependencies in the type system - no more unknown catch blocks, no more implicit dependencies - here is how to adopt it in a real TypeScript project.
9 min readPage Speed Optimization in 2026: A Developer's Guide to LCP, CLS, and INP
A practical, code-level guide to optimizing all three Core Web Vitals - with specific techniques for LCP, CLS, and INP that you can implement this week.
8 min readHybrid Search in Information Retrieval: Combining Dense and Sparse Vectors
Implement reciprocal rank fusion algorithms to merge keyword matching (BM25) with context-aware semantic embeddings.
9 min readReal-Time Feature Stores: Implementing Feast for Low-Latency ML Features
How to synchronize offline analytical feature stores with online key-value databases to feed real-time models under 10ms.
7 min readPixtral 12B: Mistral's First Vision-Language Model
Pixtral 12B processes images at arbitrary resolution without fixed patch sizes, scores 52.5% on MMMU, and is available under an Apache 2.0 license.
8 min readRunning DeepSeek R1 via Together AI: Fastest Hosted Reasoning Model API
Together AI hosts DeepSeek R1 671B on serverless infrastructure with streaming thinking tokens, OpenAI-compatible SDK, and sub-5-second TTFT - at $3/1M input tokens with no cold starts.
7 min readCLIP: Using OpenAI's Contrastive Model for Zero-Shot Image Classification
CLIP learns joint image-text embeddings from 400 million pairs, enabling zero-shot classification on any category you can describe in words - no labeled training data required.
7 min readBentoML: Package and Deploy ML Models as Production APIs in Minutes
BentoML standardizes ML model serving - package your model, define a service, and deploy a Docker container with an auto-generated OpenAPI spec and adaptive batching.