Skip to main content
← All Tags

LLM Engineering

5 articles in this category

AI NewsLLM EngineeringSoftware Architecture

MCP vs. CLI: Measuring Token Overhead in Agent Search

A comparison of SerpApi MCP and a custom CLI reveals that MCP can use 17x more tokens per call for stateless search tasks.

Read more
AI NewsKnowledge ManagementLLM Engineering

Synthadoc v0.6.0: Solving Knowledge Staleness with Lifecycle State Machines

Synthadoc v0.6.0 introduces a five-state page lifecycle and four export formats to detect content staleness without additional LLM calls.

Read more
AI NewsLLM EngineeringSoftware Testing

Custom Evals: A Unified Evaluation Framework for 17+ LLM Agent Frameworks

Custom Evals provides a lightweight, backend-free evaluation layer supporting 17+ agent frameworks with a four-layer metric system.

Read more
AI NewsLLM EngineeringModel Evaluation

Gemma 4 E2B Exhibits Configuration-Deterministic Hallucinations at Low Context

A 15-run ablation reveals Gemma 4 E2B produces a hallucinate-disclaim-retry pattern specifically at num_ctx=2048.

Read more
AI NewsAI Open SourceLLM Engineering

Building a GPT-2 Level LLM for $100: Analyzing Karpathy's nanochat Pipeline

Andrej Karpathy's nanochat project demonstrates how to train a GPT-2 level LLM for just $100 in two hours, significantly reducing costs from $43,000 in 2019. It provides a complete pipeline from tokenization to SFT, making high-performance model training accessible to engineers.

Read more