Field Intelligence
Knowledge logs from the field.
Engineering notes, research commentary, and lessons from production deployments.
The economics of agentic software delivery
Compare AI-assisted delivery proposals through accepted scope, engineering experience, reusable software and total cost. A white paper from Standard Applied.
Read white paper
Isolating AI Coding Agents on Bare Metal: Incus, Podman, and a $50/Month Server
How SAIL runs isolated, multi-project AI coding agent environments on one $50/month bare-metal server with system containers, rootless Podman, and YAML.
Read log
Notes: Defeating Non-Determinism in LLM Inference
Study notes on why LLMs give different outputs for the same prompt, even at temperature 0, and the batch-invariance fixes that make inference reproducible.
Read log
The Agency Tax: Red Flags Before You Sign
Six red flags to check before you sign with a software or AI development agency, the question that exposes each one, and what a good answer sounds like.
Read log
Instruction fine-tuning Llama 2 with PEFT's QLoRa method
How to instruction fine-tune the Llama 2 7B model with the PEFT library and QLoRA, using a custom instruction dataset to build a sentiment analysis model.
Read log