One quick things up-top: this week (tomorrow!), get an overview and demos of the private AI stack and development frameworks we’ve been working on at Tanzu. Register to check it out online, either live or the recording after the event. Spy on the DM with Model Context Protocol Servers in JavaHere’s my latest walk-through is writing Model Context Protocol Server tools…to play D&D. Here, I build some slightly more complicated Oracles and show how to do logging.

Two quick things up top: in a little over a week we’re going to talk about what what us Tanzu folks been doing with enterprise AI, register to check it out online. Next month, at Cloud Foundry Day you can come to an in-person workshop for even more. I’ll be there, hopefully talking about the goblins and AI, as well as MC’ing. Mole enchiladas at El Cerrito, Menlo Park, California.Wastebook“They’re not chasing perfection–they’re chasing momentum.

The goblins get into agentic AI. The above video is exciting for me: it’s me relearning programming, playing D&D with the robot, and coming up with a new type of way I can help out at work. In this introductory video I go over the basics of making a tool (an “MCP Server”) for Claude. This tool is a very simple oracle that will answer yes/no questions. Oracles are a core part of solo role playing and introduce unknown twists and turns, help you come up with adventures on the fly, and so forth.

Just wastebook and links this episode. Wastebook“So what is a critic for? This is the second quote that’s in my notebook. It’s in every notebook because I always write it on the first page: ‘Find a subject you care about and which you in your heart feel others should care about. It is this genuine caring, and not your games with language, which will be the most compelling and seductive element in your style.

Not much today. Found at the ITQ offices.Wastebook"decision-makers can remain irrational longer than you can remain solvent. Career advice in 2025. ”a concept as antiquated as intent.” NYTimes. “a felicitous remove.” Spicy. “Significant improvement but still issues.” Oxide and Friends. Relative to your interestsA Conversation Algorithm I Cribbed From Clinical PsychologistsWhat does “open ended question” even mean? Here’s some examples, and a conversational framework built around it. This also probably good for sales and marketing.

I’m the guest on this week’s When Shit Hits the Fan podcast. You can hear about two of my fan shattings. Here’s the podcast in Apple, Spotify, and Overcast. Favor documents over slidesSlides are an oral culture, not a written culture. Imagine civilization without writing: that’s what organizations relying on slides instead of documents are like. There are workarounds, and they tend to prove the comparison. Often, you will see a slide with a lot of words, and the presenter will apologize that there’s too much text.

To Have and Have Not, Christopher Still. Found in Leiden thrift.Wastebook“We live in the age of ‘fuck around and find out’ - of iteration and experimentation.” 8Ball wisdom. “15 years ago, the internet was an escape from the real world. Now, the real world is an escape from the internet.” Noah Smith, via Ibid.. “everything is optimized for engagement instead of meaning,” the Curmudgeon Era of life. If the likely outcome is the same, you might as well do a good job, so long as that’s fun too.

You're about to waste at least a year and millions of dollars on enterprise AI projects. Here's how to avoid it. Here’s a new article on enterprise AI from me and a co-worker. As with most maturity models, it’s 2/3 prescriptive and 1/3 “here’s some ideas that might help.” A bit of map and territory. With AI, we’re seeing a familiar anti-pattern, but this time flavor-injected with generative AI: the board charters a tiger team, gives them budget.

What we love is good for usDavid Lynch on smoking: "But that said, he admitted smoking played a huge part in his life. “I don’t regret it. It was important to me. I wish what every addict wishes for: that what we love is good for us.” He went on: “A big important part of my life was smoking. I loved the smell of tobacco, the taste of tobacco. I loved lighting cigarettes.

My first law of enterprise AI: if you end up having two robots talk with each other to complete a task, that task was bullshit in the first place, and you should probably eliminate it rather than automate it. For example, if AI is used in both sides of B2B procurement (enterprise software sales), then much of the process is probably bullshit in the first place. There is so much weird and ancient in procurement, on both sides, that it’s clearly a poorly done process and part of enterprise IT culture.