Posts by Dechive

@Dechive

Dechive

Practical notes on AI verification, prompting, structured output, workflows, and...
Korea dechive.dev Joined May 2026
1.7k Points31 Badges7 Connections7 Followers9 Following

Posts by Dechive

Dechive in Articles 8 min read
Most people start thinking about data after they launch something. They build an app. They publish a landing page. They post on social media and say: > “I made this. Please try it and leave feedback.” There is nothing wrong with that. After launc...
post-cover-21078
Dechive in Articles 2 min read
Building a blog, maintaining a website, and writing consistently may look simple from the outside. But I think they are one of the best ways to train your ability to think every day. A blog is not just a place to publish finished thoughts. It is a ...
post-cover-20760
Dechive in Articles 1 min read
Would an English version of this be useful? I recently wrote a small Korean ebook called “Validate Before You Build.” It is about vibe coding, solo building, AI SaaS, and the mistakes we make when AI makes it too easy to turn an idea into somethin...
post-cover-18940
Dechive in Articles 6 min read
For a long time, verifying AI meant checking the answer. If AI wrote an explanation, we could read it. If it summarized a document, we could compare it with the original. If it made a factual claim, we could check the source. If the answer was incom...
post-cover-18792
Dechive in Articles 4 min read
Keeping up with AI is not about trying every tool. It is about knowing which tools deserve your attention. Every developer feed now feels like a race. Someone built an app with AI over the weekend. Someone launched a small SaaS. Someone connected ...
post-cover-18721
Dechive in Articles 3 min read
AI coding tools are changing the development loop. With tools like Claude Code, Cursor, and GitHub Copilot, a solo developer can build screens, wire APIs, generate logic, and deploy much faster than before. That is exciting. But it also creates a ...
Dechive in Articles 4 min read
For a long time, good prompting meant teaching the model how to think. We told models to think step by step. We asked them to break problems down. We gave examples. We described the order in which they should evaluate conditions before giving ...
post-cover-18161
Dechive in Articles 5 min read
When we use AI in a chat window, a little extra text usually does not matter. If the model says: Sure, here is the result: before answering, we can still read it. If it adds: Hope this helps! after the answer, we can simply ignore it. But co...
post-cover-17702
Dechive in Articles 3 min read
AI workflows are everywhere now. Developers share how they use Claude Code, how they structure prompts, how they connect agents, how they automate repetitive tasks, and how they organize their projects with tools like GitHub Actions, n8n, or MCP ser...
post-cover-17585
chevron_left

Latest Jobs

View all jobs →