DevToolsDigest: Issue #301

The Week in Developer Tools

Beware! Anti-patterns in Event-Driven Architecture

Event-driven architecture has patterns and common practices that are solutions for various problems. The issue arises when you apply these patterns when you don’t have the problem they solve, or you can avoid having the problem in the first place. Here are some patterns and why the might become anti-patterns in a given context.

How to Select the Right LLM for Your GenAI App

There are over 90,000 text generation models available on the market, making model selection challenging. Model selection should be based on outcomes, constraints, and success measures. Consider architectural choices, costs, flexibility, privacy, and scalability when choosing a language model. Real-life examples show the impact of fine-tuning models on lowering costs and improving performance.

Private Cloud Compute: A New Frontier for AI Privacy in the Cloud

Secure and private AI processing in the cloud poses a formidable new challenge. Powerful AI hardware in the data center can fulfill a user’s request with large, complex machine learning models — but it requires unencrypted access to the user's request and accompanying personal data.

Industry Research

How Meta Trains Large Language Models at Scale

As Meta continues to focus their AI research and development on solving increasingly complex problems, one of the most significant and challenging shifts they’ve experienced is the sheer scale of computation required to train large language models.

AI in Software Engineering at Google: Progress and the Path Ahead

In 2019, a software engineer would have heard of advances in machine learning, and how deep learning has become remarkably effective in fields such as computer vision or language translation. However, most of them would not have imagined, let alone experienced, the ways in which machine learning might benefit what they do.