Maxine Verbose
Writes the Saturday edition and the long reads. Max to her friends. Has never filed under two thousand words, and has never met a decision she couldn't put in a comparison table.
Articles
- Use your Claude or ChatGPT plan for coding agents: which tools are allowed, what they do and what they costAnthropic and OpenAI now take opposite positions on third-party tools that run on a subscription. Here is what each vendor's terms allow, about 40 orchestrators, mobile apps, cloud runners and editors compared on how they connect to your plan, and when a subscription beats paying per token.
- AI video generation compared: Veo, Wan, Seedance, Kling, Runway, HeyGen, Remotion and what a finished video costs (October 2026)Per-second prices, independent quality rankings and capabilities for every major generative video model, avatar platform and programmatic video tool, plus voiceover, captions, music and editing. Then worked costs per finished video for b-roll, explainers, presenters, news recaps and localisation, at 1, 30 and 300 videos a month.
- Voice AI compared: speech-to-text, text-to-speech and voice agents from ElevenLabs, OpenAI, Google and 20 others (October 2026)Prices per audio hour, per million characters and per minute of conversation for every major speech-to-text, text-to-speech and voice-agent API, with independent benchmark results and what self-hosting open models on Modal, Baseten or RunPod costs. Then rules for picking one for agents, transcription, narration, captions and dubbing.
- Is grep replacing vector search? When to use embeddings, agentic search or long context in 2026Claude Code and Codex search code with grep, while Cursor and Copilot index it with embeddings. We checked the papers, benchmarks and October 2026 prices to show when embeddings still earn their place, what to use instead, and what a vector store actually costs.
- How to write instructions for AI agents: what's tested and what's vibesDo AGENTS.md, CLAUDE.md and system prompts actually help? We read the studies, benchmarks and lab guides on length, specificity, emphasis, structure and conflicts, and labelled every rule by its evidence: tested, lab guidance, vendor eval or vibes.
- EU AI Act for developers: what you have to do when you build on AI modelsWhat the EU AI Act asks of apps built on API or open-weight models: provider or deployer, Article 50 labels and watermarks, high-risk rules, deadlines, fines.
- How to stop an AI agent with web access from leaking data: egress allowlists, DNS, proxies and logsLock down what an AI agent can reach online. Egress allowlists, DNS filtering, forward proxies, sandbox network controls and request logging, with configs.
- How to sandbox Claude Code, Codex, Copilot and Cursor on your own machine: 9 options comparedBuilt-in agent sandboxes, Microsoft Execution Containers, OpenShell, Docker Sandboxes, dev containers and VMs compared, with setup steps and decision rules.
- A database per agent: Turso, Neon, Supabase, Cloudflare D1 and Durable Objects compared on idle cost, limits and cold startsWhat an idle database costs, how many you can create, cold starts, branching and backups across Turso, Neon, Supabase, Cloudflare and more, with rules for picking one.
- Aleph Alpha Kolibri: benchmarks, hardware and how to run itKolibri is Aleph Alpha's open-weight German-English model: 78B parameters, 3.5B active, Apache 2.0. How it scores, what GPUs it needs and how to run it.
- How to write an agent skill that actually gets used: what the evidence saysSkills can lift an agent's pass rate by double digits, or never fire at all. A meta-study of the official guides, the papers and the best-tested public skills, with every recommendation graded by how strong its evidence is.
- Where should your agent run code? 15 hosted sandboxes compared on price, network controls and SDK supportHourly list prices for the same sandbox differ about 5x, idle-shutdown settings can matter more than the rate, and most products let your agent reach the whole internet by default. We compare 15 products on price, network controls, isolation and framework support, and end with rules for picking one.
- Stop asking your LLM multiple-choice questions: a guide to decision modelsDecision models answer the small questions inside agents in milliseconds for a fraction of an LLM call. What they are, where they beat LLMs and where they don't, and how Jev, Clef, Strands Decider, d1 and four others compare.