What does it mean when a company says it believes business can be a force for good? Especially in the tech industry where we’re not delivering physical products and our supply chain is electronic and our people are remote so there’s no office space to green-ify.

We’re trying, learning, adjusting.

As Head of AI you may wonder if my position at NerdPress is at odds with our goals as a B-Corp? It isn’t. When a company decides to aim to be certified, and then is ultimately rated periodically, it looks at every facet of the business and does its best to be a force for benefit.

Which means the entire team does too. Yes, we’re using AI in many areas of the company. But we’re trying really hard to do so responsibly.

One real quick example (of many); a team member vibe coded a useful tool for the team. It inarguably made the team more efficient at doing their job (a win) but burned tokens like wildfire. Seeing the potential in the tool, we rebuilt it, removed 99% of its reliance on AI, and reduced its token usage to near zero.

This isn’t something we had to do. We could have just used the first version of the tool and kept right on burning tokens.

Being a B-Corp continues to remind us to look for ways to do our very best. And when we miss the mark to learn and adjust.

Lovely post by Miranda.

Aphera is the Raw photo editor built natively for Mac, with a from-scratch imaging pipeline and a workflow designed to disappear.

Built by Latent Co. (aforelinked) which includes Ryan Carver as lead singer, Naz Hamid on drums, and Juan Pablo Zambrano on guitar.

We spent five days camping in a one-bar-of-LTE-but-still-won’t-work area last weekend, so this is the first installment of the Sunday Edition in a few weeks. The days off were a good recharge, but I also can’t say it was fully enjoyable. I’m not sure a person can go from a long period of heavy work to instant shut-off without a slower pullback of sorts. I think things were too abrupt for me, and it impacted our time away.

I feel this in two ways; what is it with cellular network signal strength indicators? Are they the modern equivalent of fake progress bars?

And, also, “pullback” is a thing I’ll be aiming for prior to my next getaway. So often the period right before some time off is harried rather than relaxed. It is a sprint and scramble to make sure I get as much off my plate as possible before I step away. Perhaps I should be doing the opposite somehow?

It was so peaceful, this one week of human writing. We developed sentences from words, focussed on first drafts, and provided thoughtful feedback for each other. Our group spanned from 24-year-old students to 60-year-old design professionals, and not for a single thing in the world would I want to exchange those perspectives with some artificial machine-made fabric. I’ll try to take that spirit into my everyday life, aiming to de-pollute (is that even a word?!) my thoughts and words from the possessive narrative that “AI tools” are supposed to dominate my life. They don’t. And that’s called agency—so glad I still have that.

… I’m using AI to design AI-powered tools and I work with some people who are AI-pilled. When I get home, I read and listen to AI maximalists and billionaires’ manifestos so that I know what my executives are consuming and to get ready for what I’ll hear from them at work next week. I also follow people on the opposite spectrum, who talk about societal, environmental, and economic harms of AI, as well as predatory marketing tactics and lobbying employed by big research labs. Wading through all of that continuously takes energy and time.

I’ve been working in tech since 1994. Tech has always moved quickly and I’ve always done my best to jog along and keep up. Over the course of these decades there have been several times I’ve felt the need to sprint.

To me, a sprint is not sustainable. It is a short period of time where I must almost totally consume myself in order to do my job well. Sometimes the sprints are necessary because I fell too far behind and I needed to catch up, other times it was because I wanted to be at the head of the pack. Most of them have been relatively short-lived sprints; lasting perhaps half a year or so.

This AI sprint seems to only be getting faster and lasting longer than any other sprint I’ve experienced.

It can be argued when the sprint began. Artificial Intelligence has a much longer history than just the last few years. In fact, much of the work in the field was done before I was born. But this most recent race is the one I’m personally taking part in.

As Head of AI & Product at NerdPress, I’m obligated to keep up with what is happening in the industry, what the tools are capable of, and how best to apply them to our team’s work. It is a lot. And I feel Merlin’s words above where it is a bit consuming. But I took it on. I decided to start sprinting. I wasn’t asked to. Which I’m sure helps to make it a bit easier for me than others who were forced into the sprint.

Will it end? While I’m a little bit tired, a little frazzled, from nearly a year of all out sprinting, I think the pace is about to quicken yet again.

But now I have help. I’m no longer running alone. I have several AI agents to help me. To some, that sentence feels icky. But I’m totally OK with it. Even as the pace continues to quicken, I feel empowered to keep up much easier today than I was able to even a year ago. And I think the next year or more is going to be at least three times more work to do than the previous year.

So, I guess I’m saying that I’d better get really good at knowing when to take a short break, hydrate, shake out my legs, and get sprinting again. Because I think this is going to be a marathon and I’m here for it even after all these years.

The first version, from November 2020, was called AntiPhoto. The name was a mood. I had tens of thousands of photos and videos scattered across drives and old phone backups, and Apple Photos wanted me to live inside its library, on its terms. I didn’t want a walled garden. I wanted something that could point at a messy folder and just make sense of it.

I linked to Tyler’s project over 5 years ago. I was excited about any new Mac-based solution for photo management at the time. And I’ve tested several builds of Iris Photos since (thanks Tyler).

The 1.0 release looks great. Many of the things the app does out of the box I do within my Apple Photos library (such as have smart albums for dates and people).

The only downside (for me) about Iris Photos is that it prefers that your entire photo library exists locally… preferably directly on your Mac. I simply do not have the disk space for that. So since my reluctant switch to iCloud Photo Library I’ve been using that exclusively.

Congrats to Tyler for shipping!

Models. Models. Models.

Which model should you pick for your question, task, or goal? How much of your usage budget will you use when you do? Could it have been done by a lesser model for less usage?

As the frothy sea of AI continues to ebb and flow this seems to be one of the more challenging and hard to answer questions for those of us using AI agents to help us with our everyday workload.

The answer to this question doesn’t yet seem clear.

Orchestration; which asks a single agent/model pair to delegate work to lesser agent/model pairs is one leading answer. And it works in some contexts. For example: “Do this big task” can be planned with a larger more capable model and then delegated to one or several more sub-agents and cheaper models to do laser targeted work. In practice, this works pretty well and the tooling for this is beginning to mature to the point it happens invisibly.

But, for the most part, the leading orchestrators use their own cloud-based models (and usually only a very small subset of them). Meaning, Claude might spin up 10 sub-agents on Sonnet to do the work, but you’re limited by still needing to use an Anthropic-based cloud model.

Something I played with a fair deal is using prompt heuristics to determine which model may best suit the current task. I created a catch-all “model” that delegated to other local or cloud-based models based on the request, whether or not it included private data, etc. It works fairly well but there are so many model variants that keeping up with whatever is the latest (that can run on my hardware) is nearly a full-time job… and getting an agent to delegate the tasks rather than just single-threaded prompting isn’t easy. And isn’t something I’ve considered cracked, yet.

But I think we’ll see the solution to this question appear within the next year. And I am sort of hoping it will be in an unexpected way.

Just look at the options we have in front of us.

Take, for example, something incredible like chat jimmy. chat jimmy runs an older, less capable, Llama model but runs inference near instantly. Seriously, give it a try. It is so fast it almost doesn’t matter that it isn’t nearly as good as more capable models. Think of this; if chat jimmy needed to run 10 times to produce valuable results, it would still be 100x faster than today’s leading models.

Now, imagine if Apple, AMD, or Intel were able to take a somewhat more capable model and grind it down into the bits necessary to put directly on the silicon they ship with their products. And imagine if all agents could utilize these on-device super fast models for some tasks and only rely on the larger cloud-based models for planning and orchestration and more important things like security and testing?

I think we’re on the cusp of something like this being available. I’m already using something like it locally — a main, orchestrating agent and super fast sub-agents that only do very targeted work. But I don’t think it is the solution just yet.

As the frontier models grow, the local models are shrinking. As the frontier models chase general intelligence, the local models are focusing on very specific sets of tasks.

I think overall the gap between frontier cloud-based models and local models will only widen and, eventually, for most of our everyday work we’ll be able to use a suite of smaller models that are orchestrated by agents. The frontier models will try to solve protein folding while our local models will write website code.

It could be argued that Apple believes this already. What they call Foundation models are really just a set of models that are purpose-built for the task they are supposed to do; image recognition, speech to text transcription, emoji generation. Everything else they leave up to the frontier models.

We’ll see how it shakes out. But I think we’ll be seeing a lot more models and model variants until it is figured out.

That is, until recently.

After a long week away I found myself struggling to catch up. And I tried. I really value the insight and experiences of all the people and accounts that I follow across the web. I’ve learned so much from them. But if it stops being fun or valuable and causes me stress I thought it would be good to reevaluate my process.

I’ve taken social media breaks several times. And when I do, I declare a bit of bankruptcy rather than trying to catch up after a month or more away. Each social media break I’ve taken I found worthwhile.

Recently, though, I’ve just given up completely on the idea that I can catch up. So I think I’m over the habit of even trying to read every single post.

For the last several months, I’ve not been keeping up on reading RSS feeds or Mastodon. I fall far behind and then quickly skim the entire timeline to pick out things to read. But even that practice I’m starting to eliminate.

In NetNewswire I’ve refactored my previous setup. I used to keep folders of feeds called “Trialing” and “Subscribed”; if a feed was valuable enough for a long enough period of time it would be moved from “Trialing” into the “Subscribed” folder. Or it would be deleted. These days, I changed to a “Some posts” and “Every post” folder. The “Every post” folder is very, very small selection of feeds. So for all feeds I either read some posts or every post. And I’m slowly whittling those away.

I’ve completely given up trying to read every toot. So now I use the official Mastodon iOS application or the website (I’m no longer subscribed to Ivory as development of that app has seemed to stagnate) and I open it occasionally and read the most recent few posts and then move on with my day.

I have no desire at all to use any apps that combine multiple network feeds together. As Dave Winer would constantly remind everyone; that is what RSS is for! We don’t need all these apps! But, no one listens.

I am sort of hoping my addiction (I guess I’m willing to call it that) to social media is totally gone. I can drop in from time-to-time, see what is going on, and drop out. It is likely how everyone else uses it anyway and how I likely should have been using it all along.

I’ve done a purge of my feed reader (down to 80 feeds lol). Rather than defaulting to my phone, I’m recommitting to books as my after-lunch reading.

She goes on to list some new rules to help decide what to read online.

Readers of my blog may recall, I do this routinely. I gobble up everything for a time, then I prune (more like lopping) way way back. Then I start over.

The AI slop explosion is real and I’ve not dodged it. In fact, I’m right in the thick of it. It has been a sprint to keep up with. But I feel like my reading Tracy’s post, albeit a few months later since I’ve been so busy I’ve neglected my feed reader, is as good as any reminder to scale back and revisit my information intake yet again.

See also: 2012, 2013, 2015, 2025. And many others.

Signboard 1.5 just shipped and the landing page has been updated.

This release brings much tighter Obsidian integration (including a plugin which will be released into the community there soon) with linked notes, full folder conversion and support for Base file generation. What does all of this mean? That placing your Signboard board folder into your Obsidian Vault makes it super powerful to use the two apps side-by-side.

Here’s a Signboard + Obsidian use case; these days we’re recording and transcribing everything. Zoom and phone calls. We’re pulling down entire websites into Markdown. Allowing agents to run amok all over the web gathering research for us. Where do you put all of this data? Everyone is using Obsidian for this of course. Signboard isn’t the right place. Signboard is where you track what you need to get done, what you’re doing, and what you’ve completed. But now you can link a card with an Obsidian note or folder.

This is far more useful than it may seem. And agents know how to use it too. So now your Signboard cards, which can link other things like images and videos and documents, become your one-stop shop for everything you need to get your work done.

This release of Signboard also brings a more dense table view (in addition to the already powerful calendar, this week, day, and agenda views in the planner area).

Signboard 1.5 also extends the number of boards you can have open at once from 6 boards to unlimited boards. I find the board switcher (CMD + K) to be critical to switching between my projects. But, what I love is that the planner view brings them all together in one place – no matter how many boards I have open in Signboard.

You can also keep your system calendar up-to-date with any tasks or cards that have due dates in your Signboards by publishing a local calendar feed.

I’m super happy with where Signboard is today. There are a few little bugs in this build that I’m hoping to have buttoned up in a future bug release, but for now it has more features than most people will likely ever need. Enjoy!

Andrew Wilder, CEO of NerdPress, and I were on The Simple Pin Media Podcast Episode #462 with host Kate Ahl.

The bulk of the episode walks through 3 core features of Hubbub; Share Buttons, Save This, and Action Buttons. We discussed how publishers are using them, and how we approached building Action Buttons to deliberately empower publishers to go from “LLMs are stealing my traffic” to “LLMs can return readers to my site.”

My thanks to Kate for having us on.

I’ll write more about this release when I have time.

The blogs you read in 2012 redirect to parked domains. The forums where you learned what you know got bought, gutted, redesigned, and left to rot.

Terry must be tons of fun at parties. Way to rope us in Terry.

He redeems himself by the end:

But the actual internet — the protocols, the federated services, the plain-text commands, the open feeds, the small servers, the personal sites, the things people built when user and developer were sometimes the same word — is still right there.

Build protocols not platforms.

Tangentially related: The blog isn’t dead. It is just sleeping. and Blogging is alive and well.

WordPress is capable for the same reasons it can break from time-to-time.

But! There are ways to limit its breaking! And NerdPress excels at it.

Tina Collier, one of my colleagues at NerdPress, wrote about why WordPress sites can break and acknowledges that the stack of dependencies (PHP, WordPress, plugins, themes, custom code) can get out of alignment:

No one in this scenario is being malicious or careless — developers really would prefer their products not cause issues! — but this is how an open ecosystem with thousands of contributors behaves, and it’s why an update on your site can behave differently than it did for someone else.

One of the greatest challenges in shipping Hubbub, a NerdPress product, is the myriad of environments it can find itself running within across such a wide variety of dependencies. But we wouldn’t have it any other way.

From start to finish, this was a coordinated team effort: updates, firewall protections, client communication, and vendor collaboration all happening in parallel. It’s a good example of how we approach these situations: move quickly, reduce risk immediately, and then work toward a complete, long-term solution.

The team at NerdPress is truly amazing and always goes above and beyond for our clients. It is awesome to see this behind-the-scenes every day and I’m glad Andrew took the time to give everyone else a glimpse of what makes this company great.

Here is the insane business plan of what I would do, the thoughts of some fool on a hill halfway across the world:

No more keyboards or mouse support for iPads. Touch only. Nix half the iPad lineup, simplify simplify simplify. Gut iPadOS and rebuild it around touch fluidity and fluency and focus. Work with Procreate to expand their offerings. What is the Procreate equivalent of every creative tool? Look back to the playfulness of PushPopPress. Now, make a 12″ MacBook Air. Get rid of the other Airs. For the MacBook lineup, offer a cheap Neo, an ultra-portable high-spec Air, and powerful, portful Pros. And macOS? No touch. Good god, do not succumb to the siren call of touching MacBook screens. Instead, go into a three year period of major OS refactoring. Speed above all. Mythos harden the OS but increase malleability. What does an LLM-first macOS look like? One you can plug into and automate with ease. Make that. (Plot twist: It turns out it’s the same thing as a user-first OS.) Think about keyboard fluency. Bicycle for the mind the hell out of the thing. Make it absolutely clear about how iPads are used and how MacBooks are used. Think about them as true companions, but with no overlap. Maybe Ternus will usher in parts of this.

Somewhat recently I was in need of replacing my amazing iPad Pro 13″ from 2017/2018 and picked up a new iPad (not Pro). I’ve immediately regretted the purchase. Not just because I really should have went Pro, but also because _everything_ I’m doing these days requires macOS. iPadOS, while awesome at a very finite number of things, is nearly useless in the current work landscape.

Version 1.3.0 changes up the typeface in the card editor, and adds checkboxes next to task list items making them easier to mark as complete while retaining full Markdown syntax.

Thanks to all that have linked to Signboard, written in via email and said nice things, and have provided feedback and pull requests!

I don’t like to speak in absolutes. But all business software must be agent-ready as soon as possible.

What is an agent? An agent is an app that receives prompts, interacts with large language models, loops until it can satisfactorily resolve the prompt, and replies. Some agents know how to code, others know about making Excel spreadsheets, some try to know it all. But the models it calls are really its greatest strength.

ChatGPT is an agent that calls the GPT-5.x class of models.

Codex is an agent that is specialized in building apps (though, its skills are growing quickly) that calls the GPT-5.x class of models. Sometimes Codex-specific models.

Claude is an agent that can answer questions and write basic files. It uses the Sonnet, Opus, and soon Mythos class models. You primarily chat with Claude.

Claude Code is a version of the Claude agent that knows how to code. Like Codex. It is available on the web, in an app, and within a Terminal on the command line. It can read and write text files like crazy. Yesterday I wrote 15,000,000+ lines of code with Claude Code.

Claude Cowork is an agent too and is, I think but do not know, a fork of Claude Code specifically tailored to work with different filetypes like presentations, spreadsheets, and PDFs. It knows more about marketing and sales than coding. However, like Claude Code, it uses ephemeral apps to read and write files. (So does Claude Code and Codex. If you ask them to read an Excel document and manipulate it, it will quickly write a Python script to do that, and then trash it immediately. I’m oversimplifying it, but this is generally what it is doing.)

There are other agents like Perplexity (which works with several models), Gemini (which Google calls their agent and their primary models), OpenCode, Goose, and several others.

You can use these agents on just about any model you like. So if you don’t want to use Claude Code with Anthropic’s Opus 4.7 model, you can use it on top of Google’s open weight model Gemma4 and code locally for free if you’d like.

Agents can search and read the web. Because many agents can read as well as see, they can often browse the web, find something for you, fill out a form, and if given the permissions and credentials, buy something for you.

But that is an agent pretending to be a human. Browsing pages, clicking buttons, and filling out forms.

The agentweb, which is very quickly sprouting up all over, doesn’t have or need a visual component. It doesn’t need webpages at pretty URLs. Using APIs and protocols like MCP, agents can sign up for and use services that don’t even have a proper domain name. They can create accounts, buy things, use things, and learn how to interact with services they’ve never seen and you didn’t teach them about.

The first to see this in action have been the developers (like me). Agents can use MCPs to use WordPress plugins like Hubbub or desktop apps like Signboard, to sign up for services using Stripe’s Projects.dev, and buy things that they need to get the job done, all without ever asking me for permission. (I have my agents always ask me for permission, but I’m sure I won’t in the future). Agents can navigate the agentweb on their own, there is no need for the silly, slow, ad-ridden web sites… they just bounce from MCP to API to MCP to website, back to MCP until the task you set them out to do is completed.

The agentweb will dwarf the humanweb in a matter of years or perhaps months. More services, data sources, community connections and shopping will be done through the agentweb than on the humanweb.

The humanweb will still be here. Ready for us to fumble through, search, and bash our fists into our mouse buttons on. We’ll still laugh, cry, and be utterly joyed by great websites for many years to come. But the primary way we will all interact with the internet will be via the agentweb.

A few pull quotes:

It’s easy to fall into the trap of trying too hard to keep up, only to end up exhausted.

Eating is an essential part of living. Yet, keeping it simple is surprisingly hard.

There are endless food products, recipes, and health tips — and TV shows constantly push us to make beautiful, varied meals for our families every day.

Software developers can’t live without software. It is literally an essential part of our lives, and keeping it simple is surprisingly hard. Let’s learn from his philosophy behind his principle.

Takuya dealt with burnout last year. And he finds that Ichiju Issai, or one-soup, one-dish, approach helps him. A worthy read or listen.

Signboard 1.2.0 includes the following improvements:

• Added restore from archive view and CLI
• New color schemes: Mid-winter, Coffee, and Cozy Blush
• Added better board filtering; Today, Overdue, and multi-label select
• Added basic activity to cards: created date, list moves, etc. More to come.
• Added Tasks.md import
• Added new keyboard shortcuts
• Added new help docs in /docs
• Simplified header UI and improved vertical height
• Fixed an issue with MCP interactions with Claude

Until this release, Signboard’s archive was a black box. But now you can archive cards, lists of cards, and entire lists and be able to restore them to exactly where they were or somewhere else. It is pretty nice. I say, archive liberally!

Enjoy!

Importing from Trello was always possible (but only partially supported). Now Signboard can import far more data from Trello board exports. The Obsidian import works with just about any Markdown files created with Obsidian but especially those created using the most popular community kanban plugins.

The fun part of this update though are the new curated color schemes. Here is what they look like.

See you next Friday.

Signboard 1.1.0 is coming tomorrow and it will include curated color themes (so aesthetic) and importing from both Trello and Obsidian. And a few other nice new things.

We’ve spent 10+ years focusing on having a clean, well designed interface for Ghost. It’s something we care a lot about, and spend a lot of time on.

But within about ~1hr of using Ghost via Claude/CLI, it was hard to imagine going back to caveman-clicking around a browser to get something done. Particularly for complex or compound tasks that might require visiting several different areas of the app.

Totally.

I added both an MCP server and CLI to Signboard and I find myself constantly interacting with it. I sort of cover it a little in the video demo…

Let’s say I’m brainstorming an outdoor project for the yard. I’m getting ideas, calculating material costs, figuring out a timeline, and planning. At the end of that I would then set up a new board (or, at least a card or two) in Signboard to plan out the entire project. Now, with a Signboard skill in Claude Cowork, I do all of this brainstorming with Claude and then, at the end, ask it to create the new board and all the necessary cards, due dates, sub-tasks, custom labels etc. to hit my target due date.

As an aside: This is why I suggest keeping an eye on agentic commerce. While doing this sort of planning, if Claude could just buy everything for me (which, perhaps it already can but certainly it will be able to very soon) I would let it.

It’s like a Trojan Horse of craft: guidelines you might never agree to explicitly are guiding LLM outputs, which means you are agreeing to them implicitly.

It is worth the effort to dig under the hood of the tools we use so that we know what we may want to change. Especially so if we continue to get results we don’t prefer.

One of the things that’s most important is if I’m really proud of the thing that we’re putting out. That’s always been one of the core tenants and that goes for both the YouTube side of things and for the product side of things. If it resonates with people or not is a little bit more out of my control.

I find this is the best approach.

Colin Devroe released Signboard, a lovely little local kanban board app for your Mac. Each board is just a folder, and each card is just a text file, and when you move cards, it moves files. So deliciously simple.

Thank you Giles.