Finished reading: Incorruptible Why Good Companies Go Bad and How Great Companies Stay Great by Eric Ries 📚I listened too this one. And now will be the digital version so I can reread and annotate. Will have more formed opinions then. Suffice to say I feel like I learned a lot just not sure exactly what yet.

In this environment, AI is no longer a software selection exercise. It becomes a question of organizational architecture and the ability to connect people, processes, and technology within a unified framework.

AI boom forces companies to rethink how they measure business value

I wish there was more content in this article. It scratches the surface of what I’ve been thinking about a lot lately: how will the structure of organizations and management change because of AI?

exe.dev is a subscription service that gives you virtual machines, with persistent disks, quickly and without fuss. These machines are immediately accessible over HTTPS, with sensible and secure defaults. You can share your web server as easily as you can share a Google Doc. With built-in optional authentication, so you can focus on your thing.

What is exe.dev? - exe.dev docs

Hmm. I want to learn more about this. Could it be a way to publish and test tools for civil society?

When one of your sessions learns something another session needs, such as a finding, a status, or a decision, Claude passes it along instead of you copy-pasting between terminals. Claude discovers the target with ListAgents and sends with SendMessage, so you never call either tool yourself. Claude can decide to send a message without being asked, and you can also prompt for one.

Message your other Claude Code sessions - Claude Code Docs

I’ve had a hard time decomposing some tasks into multiple agents because of this kind of knowledge flow. Looking forward to testing it out.

The idea that they’re spending serious money on AI tokens to turn PDFs and PowerPoint decks into Markdown only makes me think I’ve overestimated the median intelligence of the people who work there.

The Tokenpocalypse Is Here: Companies Are Scrambling To Stop Spending So Much on AI

Most organizations with any history have tons of documents in a wide variety of formats, including PDF because it is very good at sealing all parts of the delivery, content and format. We’ve got to turn all that content into context.

This context influences every step. Strategy and regulation shape business decisions. Customer expectations and established UX patterns shape product decisions. Existing platforms and services constrain solution design. Coding standards, frameworks, and deployment pipelines guide implementation.

“Coding is solved” misses the point - Waldek Mastykarz

Organizations do have context and arranging that context so it is accessible to a wider group of people has always been the problem of knowledge management. AI and the utility it brings to coding has just made this more clear and across more technical domains.

The problem with AI voice is not the techniques themselves. It is the overuse of them—their deployment to describe a trip to 7-Eleven with the same rhetorical flourishes once used to send men to the moon.

[JFK’s AI Voice - Marginal REVOLUTION](marginalrevolution.com/marginalr…

The Times is “sane-washing” Trump and Kennedy, working really hard to take dangerous and extreme positions and treat them as reasonable and normal.

Sane washing

This is so dangerous.

Cloudflare is simultaneously blocking AI crawlers that harvest content without paying, while building the infrastructure for agents that do pay. That is the dual bet: charge the bots that take, and give the bots that work a cheaper, purpose-built tool to work with.

Cloudflare built a browser for AI agents. It uses 7x less memory than Chromium and runs entirely on Workers.

This is interesting. I’ve been thinking a lot about html as a window into content (that description courtesy of colleague and friend John Zoltner)and how browsers will change. I hadn’t thought of browsers for a gents, however.

We are the companies, labs, and independent builders who develop, research, deploy, or operate agents. Members compare notes on what actually works, find each other, and take on the problems no single organization can fix alone.

Agent Community — open community for agent builders

Esther Dyson is behind this. I’m looking forward to digging in.

The assumption that nonprofits are too set in their ways to respond to a rapidly changing world doesn’t hold up either. The best nonprofits operate like any tech startup: reading market conditions and pivoting to where the need is greatest. This is partly out of necessity, as nonprofits, more than any other sector, need to be constantly responsive to the shifting winds of community need and donor focus. Many have to raise their entire operating budget from scratch every single year — a pressure that breeds operational discipline and adaptability.

AI’s new millionaires want to disrupt philanthropy. They should fund what already exists | Fortune

Even more true for the smallest organizations closest to the issues.

Jessica Kingsley Publishers (JKP) has launched a new ‘safety cover’ designed to help users create privacy and discretion should they happen to be reading about potentially sensitive subjects in a public or unsafe setting.

Publisher launches safety covers for LGBTQ+ books

I’m glad this available. And so sad that it needs to be.

The engraved Mac Mini is the Patagonia vest of the AI era. The Patagonia vest signalled membership in a financial elite that valued the appearance of rugged practicality over the display of wealth. The numbered Sequoia Mac Mini signals membership in an AI elite that values local inference, open-source tools, and the ability to run an agent framework on a $599 computer rather than paying for cloud API access.

Sequoia is giving away the hardware for an AI project it cannot invest in. That is the point.

Have I posted this already? T the he numbers are out of date. Still much in the article that’s dead on. We need a symbol like this, a club for civil society.

In other words, REST is a set of architectural principles for serving resources, usually over HTTP. It is so ingrained in web development, and so standardized, that it feels strange when we do not see it.

What it means for an API to be RESTful | Andros Fenollosa

I’ve been pretty interested in this as a stand-in for single sign on when no personal or secure information needs to be transmitted. It can be used to stitch together web pages that are doing something for someone using a browser.

A view of reclaimed ranch land in Tomales Bay. Marnie, in the tent vestibule, out of the heavy morning fog, reading. The view from Coast campground, hills, breaking to trees, the ocean in the far distance. Erica, with her backpack and trekking poles, gazing up. A white-tailed kite, hanging the sky, waiting to catch something.

We’ve been building a new system for running evals against different models, prompts, and harnesses, with the goal of being able to identify the most appropriate small and inexpensive models for different categories of task.

smevals - a small eval suite for evaluating models, prompts, and harnesses | Prime Radiant

Definitely a tool for the Frugal AI suite.

Finished reading: Red Mars by Kim Stanley Robinson 📚So good that I immediately started the next book in the series. Something I rarely do. The formation of groups, interplay of power, use of AI, and control of the climate make it so applicable right now.

We made a different bet. We believed the future of professional AI would require more than general-purpose intelligence. It would require models built specifically for the domains, standards, and consequences of professional work. We believed that the distinct advantages of Thomson Reuters decades of world-class content and expertise could be best expressed in a model that we ourselves crafted.  

Thomson Reuters Built Its Own AI Model That Now Ranks Among the World’s Best - Thomson Reuters Institute

I think this applies to civil society generally and for communities of purpose within civil society, people and organizations working in food security, for example.

Something I’ve come to appreciate about MCP is that it’s much easier to reason about agent capabilities and what might go wrong than with arbitrary command execution in an open network environment - the default for most of today’s general and coding agent tools.

Stateless MCP

I wonder how this works with emerging standards like Agentic Resource Discovery.

Opposition is not a principle. The political winds will inevitably shift, leaving polarization behind. Building a better web is much more universal. Empowering people to own their identity, publish more freely, form many kinds of communities, and leave without losing everything.

Social web disconnect

The structures for community building are important.