Home, essays, projects, and operating-layer notes.

Essays, workflow notes, and systems writing.

When AI makes a fresh prototype cheap enough, starting again becomes a useful building method. Treat each version as a run: keep what you learned, then decide how much of the software deserves to survive.

AI can improve your output faster than your ability to judge it. A working database, a convincing essay, and an expensive subscription can all hide that gap.

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.

Reusable AI work is moving out of the clever prompt and into packages of context, tools, instructions, permissions, examples, and workflows.

Current agents lower implementation barriers while rewarding the domain knowledge needed to specify work, catch edge cases, and recover from failure.

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.

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.

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 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.

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?

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.

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 useful question is how much AI capability would still remain if the proprietary frontier disappeared tomorrow.

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.

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.

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.

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.

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.

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.

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.

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 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.

I write, build, and teach around AI, learning, and digital work.

A public interactive explainer showing how modern agent memory systems layer extraction, versioning, multimodal recall, and source grounding around stateless models.

A tiny agent-prep game where you build the tray an AI agent needs before it can do useful work.

A public interactive grimoire exploring AI through ritual, agency, memory, and dependence across twelve short chapters.

A public interactive map tracking major AI data center projects, locations, investment, and planned capacity.

A compact checklist for deciding whether an AI output is actually usable.

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.

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.

A supply and demand simulator for AI-exposed work units, showing how abundance can devalue tasks before whole jobs disappear.

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.

Working notes on how to move from prompt to draft to review without losing clarity.

Essays, resources, and experiments on where AI is going and how to use it.

A public interactive guide to Claude Code, covering slash commands, memory, skills, hooks, MCP servers, subagents, and workflow patterns.

Email for thoughtful AI, project, speaking, or advisory enquiries.

Small interactive apps, visual explainers, and interface sketches that are useful to open, test, and play with.

A public interactive guide to the five levels of Claude Code autonomy, from permission friction through subagents and loop hooks to evaluation-driven improvement.

Compare downloadable AI with the proprietary frontier, with sourced releases and versioned benchmark evidence checked 2026-10-14.

Build your own AI coding harness tier list with an unranked tool roster, practical notes and dated snapshots you can save and export.

A public interactive guide to agent-to-agent communication patterns, covering paired review, typed handoffs, shared threads, swarm routing, and the A2A protocol.

A small interactive demo for feeling how near-1,000-token-per-second inference changes agent loops and human attention.

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.

A public interactive guide to the split between local supervision, self-hosted mobile bridges, and cloud autonomy in mobile AI coding.

Build your own AI model tier list with an unranked model roster, notes for each placement and dated snapshots you can save and export.

Short email updates on new essays, projects, and useful AI notes from the site.

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.

Smaller builds, tools, artifacts, and prototypes linked to the ideas on the site.

A playful prompt-mixing experiment where sliders brew a reusable AI prompt recipe.

A playable inventory of tool notes, checklists, workflow pages, and reusable AI materials connected to the rest of the site.

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.

Explore the AI era month by month, with sourced releases and versioned benchmark evidence checked 2026-10-14.

Trace the evolution of large language models, with sourced releases and versioned benchmark evidence checked 2026-10-14.

Understand models, agents and orchestration, with sourced releases and versioned benchmark evidence checked 2026-10-14.

Bob Z

Subscribe

Harness Tier List

Projects Harness Tier List

Build your own AI harness tier list

Harness Tier List

Build your own AI coding harness tier list with an unranked tool roster, practical notes and dated snapshots you can save and export.

View project

Open Harness Tier List in a full tab ↗

The harness shapes how an AI model works with files, tools, context and feedback. This list is for my recommendations about those tools, based on what I would choose to work with.

The editor is available now with an unranked roster. Choose Make your own to create your list. My first personal ranking is still being prepared.

Reference evidence checked 14 October 2026

The roster retains the coding harness beside each measured model and effort setting. This capture includes Claude Code with Haiku 5.5 and Step 5 Preview, Muse Code with Wonder and Wonder Full, and Antigravity CLI with publicly available Gemini 4 Argon. Codex, Opencode, Grok Build and Kimi Code CLI retain their separate configurations.

These results describe tested systems. They do not assign my personal recommendations. Use the model tier list for model choices and Floor / Ceiling for the versioned benchmark comparison.

Rank the experience

Each harness appears once. S means first choice, A strong choice, B situational, C limited use and D not recommended. A placement should carry a reason and, where useful, a preferred model or setup. Unranked means no personal recommendation has been recorded.

Keep evidence in context

Where there is a saved benchmark result, the details show the tested model and settings. That score belongs to the tested combination, not every setup of the harness. It does not decide my tier. A harness without comparable benchmark evidence can still earn a recommendation through direct experience.

Preserve each edition

Published snapshots freeze the placements and reasons for their date. New editions show how those recommendations changed. The first personal edition is being prepared; old benchmark captures are not presented as my historical opinions.

Make your own starts a private copy. Save a dated snapshot in your browser, export a backup and import it elsewhere. That does not change the public list.

Model Tier List covers personal model choices.
The Intelligence Stack separates models, agents and orchestration.
The Useful Metric Is Cost Per Finished Task explains the practical outcome I care about.