# Bob Z > Practical AI writing, learning resources, and projects for people who want to use AI well. Canonical site: https://www.bobzhu.tech This file is a concise entry point for AI agents and LLM-assisted readers. Use the linked public HTML pages as canonical sources. For essays, prefer the Markdown sidecar links when you need lower-noise article text. ## Site Entry Points - [Home](https://www.bobzhu.tech/): Practical AI writing, learning resources, and projects for people who want to use AI well. - [Essays](https://www.bobzhu.tech/blog/): Essays, working notes, and posts on AI, systems, and digital work. - [Resources](https://www.bobzhu.tech/resources/): A playable inventory of tool notes, checklists, workflow pages, and reusable AI materials connected to the rest of the site. - [Projects](https://www.bobzhu.tech/side-projects/): Smaller builds, tools, artifacts, and prototypes linked to the ideas on the site. - [Experiments](https://www.bobzhu.tech/experiments/): Small interactive apps, visual explainers, and interface sketches that are useful to open, test, and play with. - [About](https://www.bobzhu.tech/about/): I write, build, and teach around AI, learning, and digital work. - [Newsletter](https://www.bobzhu.tech/newsletter/): Short email updates on new essays, projects, and useful AI notes from the site. - [Contact](https://www.bobzhu.tech/contact/): Email for thoughtful AI, project, speaking, or advisory enquiries. ## Essays - [The Useful Metric Is Cost Per Finished Task](https://www.bobzhu.tech/assets/agents/cost-per-finished-task.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/cost-per-finished-task/. Summary: The July 2026 model releases are argued in cost, tokens, and tool calls per task rather than leaderboard position. The harder problem is that most workflows can't say what finished means. - [GPT-Live Is the Voice Assistant I Actually Wanted](https://www.bobzhu.tech/assets/agents/gpt-live-voice-assistant.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/gpt-live-voice-assistant/. Summary: ChatGPT Voice turns speech into a control layer for real work: browse the web, steer Codex tasks, share screen context, and keep the same desktop environment moving from your phone. - [Loophole Treats Ethics Like Adversarial Testing](https://www.bobzhu.tech/assets/agents/loophole-treats-ethics-like-adversarial-testing.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/loophole-treats-ethics-like-adversarial-testing/. Summary: Loophole is not interesting because it solves ethics. It is interesting because it treats moral principles like something you can draft, attack, patch, and escalate until the real conflicts in your values finally surface. - [The SaaS Homepage Is Becoming an Agent](https://www.bobzhu.tech/assets/agents/the-saas-homepage-is-becoming-an-agent.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/the-saas-homepage-is-becoming-an-agent/. Summary: Attio, Linear, and PostHog are converging on the same product bet: one fixed dashboard cannot serve every user or every intent, so the SaaS homepage is shifting toward an agentic entry point. Chat is the router. Generative UI is what comes next. - [How Agents Actually Talk to Each Other](https://www.bobzhu.tech/assets/agents/how-agents-actually-talk-to-each-other.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/how-agents-actually-talk-to-each-other/. Summary: The next real step for agents is genuine multi-agent runtime across different harnesses: paired review loops, handoffs, shared threads, and open protocols such as A2A. - [Mobile AI Coding Is Splitting Into Local Supervision and Cloud Autonomy](https://www.bobzhu.tech/assets/agents/mobile-ai-coding-local-supervision-vs-cloud-autonomy.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/mobile-ai-coding-local-supervision-vs-cloud-autonomy/. Summary: As of March 24, 2026, mobile AI coding is splitting around where the work runs: a phone steering your own machine, or a phone watching cloud agents work somewhere else. - [Five Levels of Running Claude Code More Autonomously](https://www.bobzhu.tech/assets/agents/five-levels-of-running-claude-code-more-autonomously.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/five-levels-of-running-claude-code-more-autonomously/. Summary: Claude Code autonomy is not one trick. It starts with permission friction and context hygiene, then moves through subagents and loop hooks, and becomes genuinely useful when the system can measure whether the last iteration actually improved the work. - [Agent Memory Is Being Built Around the Model](https://www.bobzhu.tech/assets/agents/agent-memory-is-being-built-around-the-model.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/agent-memory-is-being-built-around-the-model/. Summary: The newest memory systems do not make language models inherently stateful. They build recall, updates, and temporal reasoning around the model instead. Gemini Embedding 2 is the first mass-scale vector embedding that is multimodal. - [AI Does Not Automatically Give You Time Back](https://www.bobzhu.tech/assets/agents/ai-does-not-automatically-give-you-time-back.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/ai-does-not-automatically-give-you-time-back/. Summary: AI can speed up individual tasks, but that does not automatically create more free time. From personal experience, the saved capacity gets filled by more complex tasks and higher expectations. - [AI Is Moving From Chatbots to Operating Systems](https://www.bobzhu.tech/assets/agents/ai-is-moving-from-chatbots-to-operating-systems.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/ai-is-moving-from-chatbots-to-operating-systems/. Summary: The most useful way to understand AI progress isn't by tracking model names. It's by tracking the operating model: from chatbots that only talk to systems that can plan, act, coordinate, and increasingly sit across software. - [AI Makes Expertise More Valuable Before It Makes It Less Valuable](https://www.bobzhu.tech/assets/agents/ai-makes-expertise-more-valuable.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/ai-makes-expertise-more-valuable/. Summary: Current agents lower implementation barriers while rewarding the domain knowledge needed to specify work, catch edge cases, and recover from failure. - [Astra for Writing, Fable for Coding](https://www.bobzhu.tech/assets/agents/astra-for-writing-fable-for-coding.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/astra-for-writing-fable-for-coding/. Summary: Astra feels better for writing. Fable feels better for coding. Live speech adds another use case: talking through ideas and steering a draft as it develops. - [Build Something That Stays](https://www.bobzhu.tech/assets/agents/build-something-that-stays.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/build-something-that-stays/. Summary: The useful difference is not who uses the most AI. It is whether each task leaves behind something that makes the next one cheaper, safer, or more consistent. - [Organic Software Is Not Vibe Coding](https://www.bobzhu.tech/assets/agents/organic-software.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/organic-software/. Summary: Organic software is expert-led, AI-assisted software that grows through real use. It is dynamic, but not loose: the builder keeps changing the app as the work reveals itself, while using judgement, tests, and feedback to stop the system from becoming a mess. - [The AI Function Clock](https://www.bobzhu.tech/assets/agents/the-ai-function-clock.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/the-ai-function-clock/. Summary: The common claim is that AI cannot replace your job. That may be true. But jobs are bundles of functions, and the better question is which functions are already moving closer to reliable AI handoff. - [The AI Proficiency Ladder](https://www.bobzhu.tech/assets/agents/the-ai-proficiency-ladder.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/the-ai-proficiency-ladder/. Summary: Every's eight-level AI adoption map is useful because it measures delegation, trust, context, and verification, not personal intelligence. This version expands the ladder and pairs it with a self-assessment that checks how people actually work with AI. - [The Floor and Ceiling of AI](https://www.bobzhu.tech/assets/agents/the-floor-and-ceiling-of-ai.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/the-floor-and-ceiling-of-ai/. Summary: The useful question is how much AI capability would still remain if the proprietary frontier disappeared tomorrow. - [The Future Feels Like 1,000 Tokens a Second](https://www.bobzhu.tech/assets/agents/the-future-feels-like-1000-tokens-a-second.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/the-future-feels-like-1000-tokens-a-second/. Summary: Cerebras is interesting beyond its IPO because near-1,000-token-per-second inference changes the shape of the work: draft, check, repair, compare, and return before the human loses the thread. - [The Interesting Part of GPT-5.6 Is the Routing Layer](https://www.bobzhu.tech/assets/agents/gpt-56-routing-layer-cerebras.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/gpt-56-routing-layer-cerebras/. Summary: GPT-5.6 Sol, Terra, Luna, and the Cerebras launch point at a more practical question: which lane should this work run in, how fast should it move, and when should a human stay close? - [The Prompt Is Becoming a Package](https://www.bobzhu.tech/assets/agents/the-prompt-is-becoming-a-package.md): Markdown article sidecar. Canonical HTML: https://www.bobzhu.tech/the-prompt-is-becoming-a-package/. Summary: Reusable AI work is moving out of the clever prompt and into packages of context, tools, instructions, permissions, examples, and workflows. ## Interactive Projects - [Agent Memory Architecture](https://www.bobzhu.tech/agent-memory-architecture/): A public interactive explainer showing how modern agent memory systems layer extraction, versioning, multimodal recall, and source grounding around stateless models. - [Agent Snack Bar](https://www.bobzhu.tech/agent-snack-bar/): A tiny agent-prep game where you build the tray an AI agent needs before it can do useful work. - [AI as Magic](https://www.bobzhu.tech/ai-as-magic/): A public interactive grimoire exploring AI through ritual, agency, memory, and dependence across twelve short chapters. - [AI Data Center Map](https://www.bobzhu.tech/ai-data-center-map/): A public interactive map tracking major AI data center projects, locations, investment, and planned capacity. - [AI Function Clock](https://www.bobzhu.tech/ai-function-clock/): A living clock for four AI-exposed work functions, showing Bob's month-level estimates for when specific activities move closer to reliable AI handoff. - [AI Proficiency Self-Assessment](https://www.bobzhu.tech/ai-proficiency-quiz/): A practical AI proficiency self-assessment that estimates your current operating level from chatbot use through copilot, agents, autopilot, workflows, background assistants, multi-agent work, and orchestration. - [AI Supply / Demand Simulator](https://www.bobzhu.tech/ai-supply-demand/): A supply and demand simulator for AI-exposed work units, showing how abundance can devalue tasks before whole jobs disappear. - [Claude How-To Interactive Guide](https://www.bobzhu.tech/claude-how-to-interactive-guide/): A public interactive guide to Claude Code, covering slash commands, memory, skills, hooks, MCP servers, subagents, and workflow patterns. - [Five Levels of Claude Code Autonomy](https://www.bobzhu.tech/five-levels-of-claude-code-autonomy/): A public interactive guide to the five levels of Claude Code autonomy, from permission friction through subagents and loop hooks to evaluation-driven improvement. - [Floor / Ceiling](https://www.bobzhu.tech/floor-ceiling/): Compare downloadable AI with the proprietary frontier, with sourced releases and versioned benchmark evidence checked 2026-09-09. - [How Agents Actually Talk to Each Other Interactive Guide](https://www.bobzhu.tech/how-agents-actually-talk-to-each-other-interactive-guide/): A public interactive guide to agent-to-agent communication patterns, covering paired review, typed handoffs, shared threads, swarm routing, and the A2A protocol. - [Inference Speed Lab](https://www.bobzhu.tech/inference-speed-lab/): A small interactive demo for feeling how near-1,000-token-per-second inference changes agent loops and human attention. - [Loophole](https://www.bobzhu.tech/loophole/): A public interactive explainer for Loophole, Brendan Hogan's adversarial moral-legal code system for drafting, attacking, patching, and escalating edge cases in your own principles. - [Mobile AI Coding Explorer](https://www.bobzhu.tech/mobile-ai-coding-explorer/): A public interactive guide to the split between local supervision, self-hosted mobile bridges, and cloud autonomy in mobile AI coding. - [Organic Software Planner](https://www.bobzhu.tech/organic-software-planner/): A planned companion tool for turning a rough app idea into an organic build plan: product spine, growth loop, pruning rules, AI build packet, and release rings. - [Prompt Potion Lab](https://www.bobzhu.tech/prompt-potion-lab/): A playful prompt-mixing experiment where sliders brew a reusable AI prompt recipe. - [SaaS -> Chat -> Generative UI](https://www.bobzhu.tech/saas-chat-generative-ui/): A public interactive companion to The SaaS Homepage Is Becoming an Agent, tracing the shift from dashboard-first software to chat-first entry points and then to generated interfaces. - [The AI Era](https://www.bobzhu.tech/ai-era/): Explore the AI era month by month, with sourced releases and versioned benchmark evidence checked 2026-09-09. - [The Evolution of LLMs](https://www.bobzhu.tech/evolution-of-llms/): Trace the evolution of large language models, with sourced releases and versioned benchmark evidence checked 2026-09-09. - [The Intelligence Stack](https://www.bobzhu.tech/intelligence-stack/): Understand models, agents and orchestration, with sourced releases and versioned benchmark evidence checked 2026-09-09. ## Resources - [AI Evaluation Checklist](https://www.bobzhu.tech/ai-evaluation-checklist/): A compact checklist for deciding whether an AI output is actually usable. - [AI Tool Stack](https://www.bobzhu.tech/ai-tool-stack/): A living map of the AI tools I use, what each one is for, and how I keep a large stack from turning into tool sprawl. - [AI Workflow Notes](https://www.bobzhu.tech/ai-workflow-notes/): Working notes on how to move from prompt to draft to review without losing clarity. ## Feeds and Discovery - [Sitemap](https://www.bobzhu.tech/sitemap.xml): Complete XML sitemap generated by Ghost. - [RSS feed](https://www.bobzhu.tech/rss/): Recent public posts in Ghost RSS format.