Half-ass Vibe Coding

I was on Cloud Foundry Weekly yesterday. We discussed “vibe coding.” More precisely, what I think of as “half ass vibe coding.” I get the AIs to write code for me, but then ask it questions, maybe even mess around with it myself. I think that might just be “coding with an AI assistant,” but as Nicky put it, it’s also pretty close to pair programming. I know that ChatGPT sure has a lot more personality than a lot of people I’ve programmed with - know what I mean?

Spy on the DM with Model Context Protocol Servers in Java - Solo roleplaying D&D with agentic AI, #02

Not only can you give more direction to the AI when you’re playing solo D&D with it, you can start to understand how it thinks. I walk through how to use MCP Server tools to enhance solo roleplaying with Claude (and ChatGPT, etc.) and how to get extra information about how the AI is thinking. Also, I show you how to do logging despite the weird setup Claude Desktop requires.

ChatGPT is very good at making D&D battle maps

D&D battle maps are one of the funnest parts of D&D. Just looking at them is fun, finding them can be a tiny thrill, and making them is a delightful way to spend hours of time. Oh, and using them. I’ve used Midjourney to make D&D battle maps in the past, especially to make really large battle maps. That works great! ChatGPT was never that good at it, until now.

Make an oracle with an MCP Server in Java with Spring AI - Solo roleplaying D&D with agentic AI, #01

Playing D&D with ChatGPT, Claude, or whatever is fun. But sometime you want more control over how it behaves and what it does. Check out this video for a quick tutorial on creating an oracle plugin for Claude. This “plugin” is a Model Context Protocol Server written in Java using Spring AI. Once you create the MCP Server, you can hook the oracle into Claude which will use it while you play as a simple yes/no oracle.

Broadcom’s Tanzu gets AI updates, but is definitely not Kubernetes - Purnima Padmanabhan, GM for Tanzu, explained that these updates can lower the barrier of entry for developers and allow users to more quickly run their applications with AI integration “while maintaining complete security and lower down time… Even though it’s more advanced, it’s actually easier to adopt because I don’t have to have skill sets in my developers to muck around with YAML files and configurations. I don’t have to have people know and spell the various projects in Kubernetes like service mesh or what is your service discovery.”