Skip to content
360SOFTY
HomeInsights

Insights

Ideas for building
better software.

Engineering perspectives on architecture, product development, AI, and the everyday decisions behind useful software.

From the engineering desk

Browse practical articles or follow the latest technology updates.

Subscribe via RSS →

Curated links from external sources — not 360Softy original articles.

ExternalSoftware Engineering
DEV Community

Evaluating LLM Output Quality In Production

In March 2023, GPT-4 could tell you whether a number was prime with 97.6% accuracy. By June of the same year, the same model name answered those same questions correctly 2.4% of the time. Nobody pushed a bad commit. No prompt changed in your repo. The thing behind the API just... moved. That number comes from a Stanford and Berkeley study, "How is ChatGPT's behavior changing over time?", and it's the cleanest illustration I know of the core problem with LLMs in production: the model is not a fun

aiobservabilityllm
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Mermaid Diagrams Quickstart and Cheatsheet for Developers

Mermaid is a text-based diagramming tool for people who would rather write diagrams than drag boxes around a canvas. It uses a Markdown-like syntax to describe flowcharts, sequence diagrams, class diagrams, state machines, timelines, Gantt charts, entity relationship diagrams, and more. For a technical blog, Mermaid is a very good default. The diagrams live next to the article, they can be reviewed in Git, and they are easy to update when the system changes. Static image diagrams look nice until

imagesdevdevops
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Implementing CQRS in Go: A Practical Guide to Scalable Architecture

CQRS is one of those patterns that gets oversold, overcomplicated, and occasionally misdiagnosed as a cure for plain old CRUD boredom. The useful version is much simpler: separate the code that changes state from the code that reads state, then let each side evolve for its own job. Martin Fowler describes CQRS as using a different model to update information than the one used to read it, while also warning that for most systems it adds risky complexity. Microsoft makes the same core point in mor

architecturedevgo
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Want AI to work in parallel? First give each one its own workspace

A while back I wrote about parallelism—taking one big task, splitting it, and fanning it out to several agents at once. But I left a thread hanging: when several agents edit code at the same time, what keeps them from clobbering each other? That's what this post is about. Let me start with the wall I ran into myself. The subagents an AI spins up on its own within a session—those are actually fine; it works out isolation by itself, I don't have to worry much. What burned me was the other kind: I

gitworktreeaiparallelism
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

I got tired of bloated, ad-ridden web downloaders. So I built a clean, static alternative.

Let’s be honest: the state of web-based media downloaders and extractors is absolutely abysmal. Whenever you need to quickly grab a test video, an audio file, or an asset from the web for a project, you usually have to navigate a digital minefield. You open a site, dodge three sketchy pop-up ads, close a fake malware warning, and pray you didn't just inadvertently install a browser hijack extension. It’s heavy, it’s bloated, and it’s a terrible user experience. I got tired of waiting for someone

webdevshowdevopenai
DEV CommunityRead original

Let’s start with a conversation

Tell us what you’re working on.

An idea, a challenge, or a system that needs to work better. We’ll help you understand the next step.

Discuss your project

Prefer email? [email protected]