LLM Engineering
How LLM applications get built and shipped: inference and serving, structured output, token formats, evaluation, and the libraries powering production language-model systems.
157 articles
LLM Engineering
FastLLM: How a Single Line of Code Can Sabotage AI Reasoning While Improving Benchmarks
LLM Engineering
whichllm: Hardware-Aware LLM Selection Using Evidence-Graded Benchmarks
LLM Engineering
JARVIS: The LLM-Orchestrated AI System That Pioneered Multi-Model Task Automation
LLM Engineering
Guardrails AI: Building Fail-Safe Layers Around Unpredictable LLMs
LLM Engineering
MosaicML Composer: The PyTorch Training Framework That Makes Checkpoints Hardware-Agnostic
LLM Engineering
Building a Codebase Documentation Engine with LLMs: Lessons from auto_llm_codebase_analysis
LLM Engineering
How NYU Built a Leaderboard to Track LLM Agents Hacking Their Way Through CTF Challenges
LLM Engineering
Terminal-Bench: Why Evaluating LLM Agents on Real Command-Line Tasks Is Harder Than You Think
LLM Engineering
Building Threat Models in Draw.io: How XML Libraries Turn Free Diagrams into Security Tools
LLM Engineering
AWS Lambda Layers: How a GitHub List Solved Serverless Dependency Hell
LLM Engineering
Building API Documentation from Network Traffic: Inside Postman's Observability CLI
LLM Engineering
Gepetto: Teaching IDA Pro to Think with Language Models
LLM Engineering
Inside Hugging Face Tokenizers: How Rust Powers Sub-Second NLP Preprocessing at Scale
LLM Engineering
How Open-Assistant Built a ChatGPT Alternative with 160,000 Crowdsourced Conversations
LLM Engineering
Stanford Alpaca: The $500 Experiment That Democratized LLM Fine-Tuning
LLM Engineering
OpenAI Evals: Building a Declarative Framework for LLM Benchmarking
LLM Engineering
Dalai: The Time Capsule That Democratized Local LLMs
LLM Engineering
Kor: Extracting Structured Data When Your LLM Doesn't Have Function Calling
LLM Engineering
GPT4All: Running Production LLMs on a 2015 MacBook
LLM Engineering
Unlimiformer: Turn Any Transformer Into a Long-Context Model with Retrieval-Augmented Attention
LLM Engineering
StructGPT: Teaching ChatGPT to Query Databases Without Fine-Tuning
LLM Engineering
Prompt Optimizer: Cutting LLM API Costs by Compressing Tokens Without Model Access
LLM Engineering
AIx: ProjectDiscovery's Minimalist CLI for Piping Unix Philosophy into GPT
LLM Engineering