chore: sync content to repo (#10036)

Co-authored-by: nilbuild <4921183+nilbuild@users.noreply.github.com>
2026-08-30 17:57:21 +08:00 · 2026-06-01 19:33:42 +02:00
parent 0de347c063
commit abc3975b8d
8 changed files with 13 additions and 18 deletions
@@ -1,8 +1,9 @@
-# Codex
+# ChatGPT

-Codex is an AI model developed by OpenAI that translates natural language instructions into functional code. It acts as the engine behind many modern programming assistants, allowing developers to describe what they want to build in plain English and receiving the corresponding code snippets in return.
+ChatGPT is a large language model chatbot developed by OpenAI. You can give it a prompt, and it'll generate text that attempts to answer or continue the conversation. Think of it as a super-smart auto-complete that can understand context and hold a conversation. It's been used for things like writing code, answering questions, and even creative writing.

 Visit the following resources to learn more:

- [@official@Codex Docs](https://developers.openai.com/codex)
- [@video@Codex Crash Course](https://www.youtube.com/playlist?list=PL4cUxeGkcC9iDBeA8IyR1IE1kl4w5IDEG)
+- [@official@ChatGPT](https://chatgpt.com/)
+- [@official@ChatGPT Overview](https://chatgpt.com/overview)
+- [@video@ChatGPT Tutorial - A Crash Course on Chat GPT for Beginners](https://www.youtube.com/watch?v=JTxsNm9IdYU)
@@ -1,7 +1,6 @@
 # Ask Al to create a list of possible causes

-Articles
-========
+If a bug keeps coming back after fixes, ask AI to step back and list all the possible reasons it could be happening. This forces a more systematic approach and often surfaces the real root cause instead of just patching symptoms.

 Visit the following resources to learn more:

@@ -1,7 +1,6 @@
 # Illustrate AI with Examples

-Articles
-========
+Always give AI something to look at, not just something to read. Paste in existing files, attach screenshots, or link to references. The more relevant material you provide, the less it has to guess and the better the output will be.

 Visit the following resources to learn more:

@@ -1,7 +1,6 @@
 # Prompt the error message and let AI do the rest

-Articles
-========
+When something breaks, copy the full error message and paste it directly into your prompt along with a short description of what you were doing. In most cases, this is enough for AI to find the problem and suggest a fix without any back and forth.

 Visit the following resources to learn more:

@@ -1,7 +1,6 @@
 # Tell AI to add logs

-Articles
-========
+Keep track of the mistakes AI keeps repeating and include them in your prompts. Telling AI what to avoid is just as important as telling it what to do. A simple line like "do not add placeholder data" can prevent a lot of unnecessary back and forth.

 Visit the following resources to learn more:

@@ -1,7 +1,6 @@
 # Use "act as" framing when helpful

-Articles
-========
+When you want a specific type of thinking, tell AI to take on a role. "Act as a senior developer" or "act as a UX researcher" shifts how it approaches your question and gives you more relevant, role-specific advice than a generic prompt would.

 Visit the following resources to learn more:

@@ -4,6 +4,6 @@

 Visit the following resources to learn more:

- [@article@https://roadmap.sh/vibe-coding/tutorial](https://roadmap.sh/vibe-coding/tutorial)
- [@article@https://roadmap.sh/vibe-coding/best-practices](https://roadmap.sh/vibe-coding/best-practices)
+- [@article@Vibe coding tutorial: Build your first app with Claude Code](https://roadmap.sh/vibe-coding/tutorial)
+- [@article@Vibe Coding Best Practices: How To Get Consistent Results](https://roadmap.sh/vibe-coding/best-practices)
 - [@article@The 10 Best Vibe Coding Tools in 2026: Our Choices](https://roadmap.sh/vibe-coding/best-tools)
@@ -1,7 +1,6 @@
 # Work step by step rather than trying to build all at once

-Articles
-========
+Build one feature at a time. Ask the AI to do it, test it, make sure it works, then move to the next one. If you ask AI to build too many things at once, things will break, and you won't know why. Small steps make debugging easy because you only changed one thing, so you know exactly where the problem is.

 Visit the following resources to learn more: