Read
Four Flash Models on Practical Prompt Tests
GLM-5.3-Flash led this four-model benchmark at 4.83 and had the lowest completed-response latency, while Qwen3.8-Flash had the lowest recorded cost.
Articles
Read
How much can you build on an 11-hour flight?
I reconstructed one LHR to SFO flight from Mission Control, git, and Linear: 5 hours 46 minutes of active work, 27 merged PRs, and several limits the logs cannot explain.
Read
I finally hit the SuperGrok limit
What it took to use a full $30 SuperGrok weekly allowance: 31 coding-agent sessions, 9.66 million input tokens, and a lot of deliberate work.
Read
DeepSeek V4 Flash vs Pro on Practical Prompt Tests
DeepSeek V4 Pro scored 4.50 to Flash's 4.38 in one practical prompt-test batch, but cost about 21 times as much for candidate answers.
Read
Grok Imagine: a small hands-on image review
Four create and edit calls through Grok Build image tools: what held up for decorative site assets, what this sample does not prove, and when I still reach for code or real screenshots.
Read
July 2026 agent usage, measured
A July extract from the Fedora Mission Control hub: 402 sessions across hosted agents and local OpenCode with Qwen 3.6 plus Hermes, alongside $14.46 of separate Direct API Spend.
Read
Local Gemma vs Grok 4.5 and Sonnet 5 on Practical Prompt Tests
A model-prompt-tests run that put a local Gemma candidate next to Grok 4.5, Sonnet 5, and GPT-5.5: peer scores, latency reality, and what a high local score does not prove.
Read
astro-llms: llms.txt from Astro content collections
A content-collection-first Astro integration for curated llms.txt agent surfaces. Why HTML scraping is the wrong default, how setup works, and what the build emits.
Read
Mission Control: provider spend, budgets, and burn rate
Mission Control now pulls account-level billing from provider APIs, surfaces Direct API Spend on the homepage, and adds budgets, burn-rate forecasts, and spend alerts without mixing them into agent session costs.
Read
Kimi sold out: capacity-constrained AI demand
Moonshot AI's Kimi subscriptions sold out. That is a capacity signal, not a demand problem: when labs turn away paying users, compute cost is the binding constraint.
Read
OpenAI model naming and independent release lines
Why version-coupled model names break down as product lines multiply, what Anthropic's shift away from shared version labels fixed, and a guess at independent OpenAI lines with their own ladders.
Read
Adding Grok support to Mission Control
How Grok Build CLI became a first-class source in Mission Control: desktop collector, source filter, sessions, activities, and honest status lights.
Read
Grok Build for Code Review in Claude Code
A look at grok-plugin-cc, a Claude Code plugin that routes review and rescue workflows through xAI's Grok Build CLI, with setup, safety gates, and test results.
Read
Mission Control: unified AI usage after the OpenClaw pivot
What Mission Control is today - a multi-source usage and runtime dashboard - and how it was rebuilt from an OpenClaw-only activity feed into collectors for Claude Code, Codex, Hermes, ComfyUI, and more.
Read
Grok 4.5 vs Sonnet 5 on Practical Prompt Tests
A benchmark writeup comparing Grok 4.5 and Sonnet 5 across 13 practical prompt tests, with methodology, caveats, and raw artifacts preserved in model-prompt-tests.
Read
Local Models for Code Review in Claude Code
A look at local-model-plugin-cc, a Claude Code plugin that routes review and rescue workflows through the Codex CLI and local OpenAI-compatible model servers.
Read
Benchmarking Model Prompt Tests
Introducing the first benchmark runner for model-prompt-tests: a small harness for running prompt suites across model providers, scoring outputs against rubrics, and publishing comparable reports.