Testing Small Local LLMs on Modest Hardware: A Portable Workflow
A repeatable way to download, serve, benchmark, and choose small GGUF models for Hermes and coding-agent work across different CPU and memory budgets.
Writing
254 posts. Browse by category or tag, or use search.
Local Gemma with Hermes: Cheap Delegation for Rails Maintenance
A practical guide to using Hermes Agent with a local Gemma model for routine coding work, while reserving cloud models for tasks that genuinely need them.
Agent 基建的三层爆发：电脑、运行时、技能方法论
从 Prime Agent、Cloudflare Computer、agent-skills、mattpocock/skills 和 Superpowers 看 Agent 基础设施正在如何从聊天框走向持久工作台、长任务运行时和工程方法论。
Tightening a dev VM that was quietly living without a firewall
What a routine security audit found on a small always-on dev VM: passwordless databases, no host firewall, over-privileged jobs, and how it got fixed.
Golden Rules for Cheaper, Safer LLM Agents
Notes on turning repeated AI workflows into scripts, skills, cron jobs, and guardrails so agents become cheaper, safer, and more useful over time.
Loop Engineering and Graph Engineering: Working With LLMs
A practical reflection on prompt, context, memory, loop, and graph engineering, and what each layer reveals about working with LLMs day to day.
When an Always Free server gets smaller
What Oracle's smaller Ampere A1 Always Free limits mean for a self-hosted ARM server, and how I redesigned mine around a 12 GB, 2-core budget.
The CI failures that moved every time you reran them
How a moving set of Rails CI flakes exposed shared download state, Selenium stale-node retries, and specs asserting before the browser settled.
Rebuilding a Small k3s Host Without Making It Precious
Notes from wiping an old single-node k3s setup and rebuilding it with a smaller, cleaner baseline for ingress, certificates, and persistent storage.
Life Is Not Git
A personal reflection on Life OS, LLM memory, and digital twins: why being perfectly archived and searchable is not the same as being alive.