Crank.report Survey

Next boring tiny tool

I’ve been using Epilogue for a while to keep track of the books I read and finish, and the big list of books I want to read. The problem is I never open the too read books when I’m on Libby to check out my next batch of books.

I did a little bit of reasearch with Gemini and learned I can make a script that can check for availability on Libby or at my branch library and send me an email or drop a note in my Obsidian vault when a book on my list is available. I think I can also add a badge to the page to show available books so I can use the published page itself as a reference.

Now I’ve got my next boring tiny tool. I will report back when it is done.

The problem from skipping laying out the constraints is that you get a disjoint patchwork that randomly prioritizes some interactions over others. AI exacerbates the draw to wackamole design. It encourages prompting “Make X more prominent” or “Add an affordance to do Y”. In the end, more users are confused.

Ref - How I Design with AI.

This is true for so much editing and change.

So the collateral chain is short. A European lender is ultimately underwriting one American company’s continued appetite for compute it does not own. If the lease goes, the chips stay.

Lambda inks $1B private debt for Nvidia chip deal

This looks like large corps moving the risk.

Modern coding agents have become so effective at finding flaws that the slightest hint at a new bug can be enough information for them to find it, something Anil has been able to demonstrate using his own agents, switching to DeepSeek V4 Pro⁠ when Claude Fable refused the task.

Just a rumor of a bug is enough

If you expect your students to choose books, ideas and genuine learning over shortcuts and distraction, you must be a bit courageous, too. Return to the basics. Cut through the haze of abstraction, the webs of scholarly terminology, the pretense of professionalization and attempt to recover the basic human experiences that can move us. Remain a student in earnest.

I let my students watch me struggle with a masterpiece. It changed everything.

This kind of engagement is also required of managers.

Good leaders do more than issue instructions. They share context, explain the desired outcome, set boundaries, and respond to what comes back.

The same habits improve my work with AI. A good prompt helps, but a shared working context helps more. Examples, corrections, and reusable instructions reduce misunderstandings. Over time, the system becomes better aligned with how I think and what I need from it.

The investment is not in pretending that AI is human. It is in becoming better at expressing intent.

Working With AI Feels More Like Leadership Than Coding — Allen Bargi

This.

There are legitimate conversations happening now to explore open source harnesses (opencode/pi) and open weight models at the company in order offset the costs associated with going through a standard provider.

Is the industry ready for tokens-constrained work? | Hacker News

From the comments on an article. I’m interested in how we set these harnesses up for small civil society organizations.

Being efficient with tokens doesn’t mean using fewer of them overall. It means making sure the ones you do use go towards the thing you actually asked for.

So let’s look at what decides the price of a token, then what decides how many of them a session sends, and along the way, what that means for how you run a session.

Maximizing the value of your Claude Code sessions | Claude by Anthropic

Good tips for Frugal AI usage. Written for developers. But easy to understand the principles and apply them to a variety of AI work.

The main object of AI security policy should be to understand this picture and figure out how to minimize overall net harms given AI’s affordances for both attackers, defenders, and victims given surveillance information about both groups.

We urgently need a coherent national AI cybersecurity policy

We need to think about this for civil society. How are investing in the ability of organizations of all sizes to operate in the changing cyber security landscape.

Why not one agent for everything?

This might be pointless, but the main reason is least privilege. Some agents don’t need access to GitHub, deployments, or my calendar. Why increase the blast radius and potential for mistakes if I can avoid it? Just like humans…?

Chad Arimura | My agent setup

How to decompose a task into how many agents is something I think about all the time.

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.