AI Newsletter #1

There is a lot going on in today's technological world, but the most intense and vibrant area is undoubtedly the field of artificial intelligence. After brainstorming, our Java Champion Education group agreed to create a newsletter with a 14 days cadence. In our newsletters, we will include a collection of recently read interesting resources in the field of artificial intelligence with a short description.

Although the stream of published articles is very large and the ability to read them all is an illusion, the published selection, such as the below is implicitly narrowed. The purpose of the AI Newsletter is to help everyone stay informed and expand their knowledge in areas related to artificial intelligence.

Each record, as shown below, will hold a simple format, as following:
article: [number]
link: [title, link source]
desc.:[text]

Let's start the first iteration with a batch of interesting reads:

article: 1
link: GitHub CEO: manual coding remains key despite AI boom
desc.: The articles describes the importance of manual coding abilities and deep platform understanding. quote: “The worst alternative is trying to figure out how to provide feedback or prompt to describe in natural language what I already know how to do in programming language” Dohmke. Relation to VibeCoding

article: 2
link: Expert Generalists
desc.: Provides an overview of the importance of "Expert Generalist" people for problem solving during complex application development. The article outlines several scenarios of how "Expert Generalist" approaches challenges compared to specialists. The article discusses the use of LLM technologies.

article: 3
link: Emerging Patterns in Building GenAI Products
desc.: The article attempts to structure known ways of using LLM into patterns. It discusses their advantages and disadvantages. The article offers a closer look at their use.

article: 4
link : Complex, AI-generated software projects will never happen
desc.: The article describes a personal perspective on how the use of AI agents negatively affects the desired project goals. It discusses the usefulness and contribution of developer skills, including the impact for future development.

article: 5
link: Silicon Valley Insider EXPOSES Cult-Like AI Companies | Aaron Bastani Meets Karen Hao
desc.: This video is a review of book author Karen Hao: Empire of AI: Inside the reckless race for total domination

article: 6
link: LLMs brining new nature of abstraction
desc.: This article points out the non-deterministic nature of the results generated by LLM.

article: 7
link: Using ChatGPT as a technical writing assistant
desc: The article describes a scenario where an AI-LLM agent is used to deliver content based on a requested narrowed input. While the ending may seem optimistic, it reveals the difficulties and the necessity of human assistance and ownership to ensure that the content provides value.

article: 8
link: Smaller LLM AI models for Java code
desc.: The article explores the growing trend of smaller, more efficient Large Language Models (LLMs) for Java code generation, contrasting with the previous "bigger is better" approach in AI development.

article: 9
link: MCP Vulnerability Exposes the AI Untrusted Code Crisis
desc: The article identifies the scope and impact of the use of agent-based AI tools. It describes the implications of using the Model Context Protocol (MCP) used by agent-based AI. How it impacts the industry and exposes businesses to potential threats. The article suggests a level of mitigation measures.

article: 10
link: Legacy Modernization meets GenAI
desc: The article discusses the use of an LLM agent to gain a general overview of a legacy system. An attempt to describe the modernization of such a system, extraction of business rules, events, etc. highlights additional challenges.

article: 11
link: Spec-Driven Development with AI: A New Approach and a Journey into the Past
desc: The article discusses the importance of properly understanding business requirements. It discusses the potential benefits of AI agent technologies as part of the development process. It emphasizes the need for human intervention and participation in this process.

Conclustion

We hope you enjoyed the first newsletter on artificial intelligence. We are already preparing the next one. Please feel free to give us any feedback, we look forward to further development of the AI newsletters initiative.

Enjoy reading AI,

JC-AI Newsletters

• AI
• Design Patterns
• GenAI
• Java
• LLM
• Machine Learning
• Research
• Videos

Miro Wengner

Author

Miro has been a member of the Java Community Process (JCP) for a long time. He contributes to the OpenJDK and Mission Control project. His focus is on Java performance and maintainability. Miro has also contributed contributing to various other open source projects such as OpenTracing, Pi4J, and more. He is also co-author of the Robo4j project which has been awarded the Duke's Choice Award 2017. Miro has been recognized as a Java Champion, Oracle ACEPro and JavaOne Rock Star speaker. Aside from his daily duties as a Principal Engineer at OpenValue, he shares his knowledge at conferences (JavaOne, CodeOne, Devoxx, GeeCON etc.) and blogs.