GuidesNeovim LLM Setup: Adapters, Keys and Custom Endpoints
Wire a Neovim LLM plugin to your own OpenAI-compatible endpoint — how adapters are shaped, where the key should come from, and why streaming often looks broken.
ReadNotes on models, agents, and what inference costs
Practical writing for developers building with large language models — how they work, how to pick one, and how to keep the bill predictable.
Guides
ModelsOpen Model Pricing Compared: What the Per-Token Rate Hides
Input and output rates across the open-weight field, and why the cheapest model per token is frequently not the cheapest per completed task.
Read
ModelsOpen-Weight Model Licences Compared: What You Can Ship
MIT, custom terms with revenue thresholds, and everything between. Which 2026 open-weight models you can build a product on without conditions.
Read
ModelsOpen-Weight vs Closed Models: What the Gap Costs You Now
Closed models still lead on aggregate benchmarks, but the gap narrowed sharply through 2026. What open weights buy, what they still cost, and how to decide.
Read
GuidesOpenAI Node SDK Setup Against a Custom Base URL
Configure the official Node client for any OpenAI-compatible endpoint: retries, timeouts, abort signals, streaming, typed errors and the runtime traps in serverless.
ReadGuidesOpenAI Python SDK Setup for Any Compatible Endpoint
Configure the official Python client against a custom base URL: retries, timeouts, async, streaming, tool calls and the error hierarchy you should be catching.
ReadGuidesopencode Setup Guide: Custom Providers in the Terminal
Configure opencode against your own OpenAI-compatible endpoint — the provider block, model naming, per-mode model choice, and how to verify tool calls work.
Read
AI AgentsOrchestrator-Worker Patterns for Agents That Hold Up
The orchestrator-worker shape is the one multi-agent design that reliably pays for itself. Here is how to build the lead, the brief and the synthesis step.
Read
FundamentalsPaged Attention: Virtual Memory for the KV Cache
Paged attention stores the KV cache in fixed-size blocks instead of one contiguous slab, which is what lets a server hold far more concurrent sessions.
Read
AI AgentsParallel Tool Calls: When Concurrency Helps an Agent
Running tool calls concurrently cuts wall-clock time but not tokens, and it is only safe for some operations. How to decide what to parallelise.
ReadAI AgentsPartial Failure Recovery: When Half the Agents Succeed
Six workers, four returned, two timed out. Whether to answer, retry or abort is a design decision — here is how to make it before the incident, not during.
Read
Cost & PricingPer-Seat vs Per-Token Pricing: Which One Fits Your Team
Per-seat billing meters people, per-token billing meters work. Here is what each optimises for, which workloads each punishes, and how to model both.
ReadShowing 517–528 of 731 articles