Blog de Joe Freeman

Here are three short videos I did after reading a bunch “AI is blah blah to programming” posts on LinkedIn. Maybe not yet to binary Never another general purpos programming language The future is domain specific languages (DSLs) Revision History Created 2025 07

The hot ticket right now is "Put AI Everywhere". This usually results in a race to come up with ideas about how AI can be used in new products or existing systems.  I suggest creating a system to analyze existing processes, software, and programs with a structured approach, identifying opportunities and assessing risks and rewards. LLM agents, chat bots and instructors models that turn human speech and writing patterns into content or actions is in scope here.  TTS, STT, translators and other non integrated LLM uses are out of scope. The talk below iteratively breaks down our process until we reach the point where we identify AI opportunities. We start with PDCA (Plan-Do-Check-Adjust) as a notion for the lifecycle of products, software, and processes. We can map that into the following in the software space. Item 4 could be anything specific to your domain.  Design Time: All of the processes that happen before actual code execution. This is before transactions, customer ...

LLM-supported AI is being stuffed into every computer-based and computer-assisted process. A lot is being said about the benefits of LLM, with some secondary discussions about security and behavioral risks. Many of the risk discussions have been unstructured bullet points or anecdotal stories of hacked systems. The OWASP Top 10 for LLM Applications 2025 provides a framework for understanding the top risks of an LLM-integrated system. The OWASP Top 10 for LLM Applications deserves the same attention the OWASP Top 10 for Web applications has held for over a decade. The Developer's Playbook for Large Language Model Security  by Steve Wilson provides a solid foundation for understanding risks existing in an LLM ecosystem. It also led me to the  OWASP Top 10 for LLM Applications 2025 .  This is a great resource for anyone looking to integrate LLMS into business processes or existing systems. I got this book as part of a set of O'Reilly books in a Humble Bundle. OWASP Top 10 fo...

Anthropic released an npm package for claude-code  that acts as an LLM coding assistant. Anthropic  on their website  including sample LLM interactions. This blog article exist to make it easier to read the prompts and provides no analysis or value judgement. Claude-code Typescript source is available on the npmjs site. Their source provides some interesting examples of good prompt engineering. They show how you can create a detailed system prompt to achieve better results.  I've extracted some of the prompts here to make them easier to read.  I've wrapped some of the text to make it easier to read.  I have no idea if the extra new lines impact the results. So copiers be aware. Claude-code on npmjs https://www.npmjs.com/package/@anthropic-ai/claude-code?activeTab=code The npmjs links to the GitHub repository with the source are broken at this time (2025 02).  cli.mjs I found the following system prompts while scanning cli.mjs. systemPrompt : [ `Your ta...

Some people buy computing power for self-training or self-edification projects. Others rent computing power. I like owning the gear I work on. I purchased a desktop to be used as a gaming machine, a development system, a containerized workload machine, a Data Science machine, and a Machine Learning platform. I didn't understand that it would turn into a series of hardware upgrades bound by PC architecture constraints. This was a great learning experience, but not the best raw dollars investment from a pure cost/capabilities point of view. The 3 years of upgrades cost $1200. I saved some money by purchasing previous-generation hardware. Buying current-generation hardware upgrades would cost $1900.  I could have stopped anywhere on the path. Apple wasn't a player in the gaming, M/L, or GPU market when I made my purchase. Apple has caught up for most of my use cases with its large shared memory architecture and performant CPUs. A MacBook might be the simplest approach for someone ...