Topic desk · 5 guides
Build & technical
Agents, coding assistants, local models, and harness work.
Latest in this topic
5 guidesLocal LLMs in 2026: What Actually Runs on a Laptop Now
What a freelancer can actually run locally in August 2026: Qwen 3.8-27B on a 32 GB Mac, why full DeepSeek V4-Flash is not a laptop job, and a one-weekend experiment.
From Prompts to Systems: The Agent Engineering Basics That Matter in 2026
As of August 2026, prompt skill is baseline. A freelancer can build a production-shaped agent with free or self-hosted infrastructure components; model inference is a separate cost or local choice.
How to Run a Multi-Model Content Pipeline on DeepSeek Harness (Field Test)
A field test of running Grok, Claude, and Codex as one content pipeline on DeepSeek Harness—roles, real commands, subscription-quota cost, and when the extra steps are worth it.
Should You Use AI Coding Assistants on Side Projects, or Only for Clients?
A practical test for deciding whether agentic coding tools earn their keep on personal, unpaid projects—and where they quietly cost you.
How to Choose an AI Code Assistant as a Freelancer
A practical guide to choosing between autocomplete, chat-based, and agentic coding assistants based on your work, risk tolerance, and budget.