Generative AI fundamentals
Build a practical understanding of generative ai fundamentals from the underlying principles.
EXPLORE · 17 ARTICLES
Learn why AI produces its answers and how to judge tools by their real utility, safety, and fit for the job.
Topic map
Build a practical understanding of generative ai fundamentals from the underlying principles.
Build a practical understanding of using ai effectively from the underlying principles.
Build a practical understanding of ai product comparisons from the underlying principles.
Build a practical understanding of developer tools from the underlying principles.
Start here
A guided path from fundamentals to the next step.
When you ask ChatGPT something and receive an answer, it is easy to assume that it found a stored correct answer and showed it to you—like finding a document after entering a query in Naver or Google. But AI does not work that way. This misunderstanding leads to confusing experiences such as “AI lied” or “AI keeps changing its answer”…
Read articleWhen people say, “I tried AI, but it wasn’t great,” many stopped at one-line requests like “Write an email” or “Summarize this report.” Yet even a small refinement to the request sent to AI—the prompt—can make the output feel as if someone else wrote it. There is a grand name for this: prompt engineering…
Read article"So which one should I use? Do I need to pay?" Here are the answers as of mid-2026. The short version: no AI is best at everything. Choose based on your use case. All three now have useful free plans, so you can use them free first and pay only after finding your limits.
Read articleAll articles
Throughout this series, I urged you to attach materials. This time, we apply the brakes. Can you paste company documents into AI? Customer lists? Can you use AI-written copy directly in ads? This is not legal advice; it is a practical guide to the boundaries every general user should know.
Read articleAfter working with AI for a while, something odd happens. It asks again about conditions you clearly set earlier, undoes fixes made above, and quietly ignores instructions from the start of the conversation. Even pointing out, “I already told you that,” helps only briefly. It isn’t broken. This comes from how AI itself handles conversation memory, and once you understand the principle, the solution is simple.
Read articleGitHub is full of useful projects nobody knows about. Some lie buried with only a few stars before suddenly becoming popular. This series opens such repositories one by one to see what they do, how they were built, and whether they are actually useful.
Read articleThe previous two articles boil down to this: AI fails when it relies on its own memory. When that memory is outdated (knowledge cutoff) or fuzzy (hallucinations), it starts filling gaps with plausible guesses. The solution is equally simple: make AI answer from the sources you provide instead of its own memory.…
Read articleI asked AI to research sources, and it gave me a polished list with paper titles and authors. A search revealed that the papers did not exist. If you have used AI for a while, you have probably had a similar experience.
Read articleAsking AI to build a website is easy now. The real struggle starts afterward—when you show the finished screen and say, “This button looks a little odd.”
Read articleFor a while, the terminal was a tool you used when available. As the IDE became the center of development, the terminal was relegated to a secondary window for checking build logs. But after 2025, everything changed. Claude Code, Codex CLI, Gemini CLI…
Read articleFor developers using a Mac, the terminal is probably the app they keep open the longest each day. Yet surprisingly, many people keep using the default Terminal for years.
Read articleOpenAI has launched its new voice model, GPT-Live. If I had to pick one key sentence from the announcement, it would be this: "A full-duplex architecture that listens and speaks simultaneously." No matter how fast previous voice AI became, it was still a walkie-talkie: one side had to finish speaking before the other could respond.…
Read articleThe question “Which should I subscribe to, Claude or ChatGPT?” can no longer be answered by comparing model performance alone. As of July 2026, the top models on both sides (Claude Fable 5 and GPT-5.6 Sol) score 60 to 59 on overall intelligence—effectively a tie. The difference lies in the ecosystems: what they can and cannot create for you.
Read articleIt has been three months since we introduced an AI code review tool to the team.
Read articleThese days, many more people are writing blog posts with AI tools such as ChatGPT and Claude. If you take it a step further, you may even start wondering, "Why not automate everything from generating the post to publishing it?"
Read article