Je teste ChatGPT Codex SANS savoir coder (une TUERIE !)

Je teste ChatGPT Codex SANS savoir coder (une TUERIE !)

by Ludo Salenne

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 Ludo Salenne 👥 267K 📅 May 20, 2025 ⏱ 29 min 👁 62K 📄 tutorial 🧭 2026-08-21
Available in: English (current) Français

Keywords

ChatGPT Codexno-codeAI agentGitHubBolt

Summary

In this tutorial, Ludo Salenne, a non-coder, explores OpenAI’s ChatGPT Codex, an AI agent specialized in programming. He explains what Codex is, its features, and how it can be used by both developers and non-developers. The video demonstrates connecting Codex to a GitHub repository, using the ‘Ask’ and ‘Code’ functions, and fixing a bug in a chess application. Then, he shows a workflow for creating an app from scratch without coding: using a no-code tool like Bolt to generate a basic app, exporting the code to GitHub, and then using Codex to improve and refine it. He highlights Codex’s ability to work in parallel, its sandbox environment for safe testing, and its integration with GitHub for version control. The video concludes with instructions on how to activate Codex and a reminder to subscribe to his second channel.

137 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a practical, hands-on demonstration of ChatGPT Codex, which is valuable for viewers interested in no-code development. The creator’s approach of testing the tool as a non-coder adds credibility and makes the content relatable. The argumentation is straightforward: Codex is a revolutionary tool that democratizes coding. The step-by-step process is clear and easy to follow, and the real-world example of creating an app from scratch effectively illustrates the tool’s potential. However, the video is largely promotional, with the creator frequently plugging his own resources and second channel, which can detract from the objective value of the information.

Scientific Rigor, Source Quality, Title Accuracy

The video is a tutorial, not a scientific analysis, so the rigor is appropriate for its purpose. The creator cites the official OpenAI announcement and GitHub as sources, which are relevant and authoritative. The title accurately reflects the content, and the video delivers on its promise. The creator is transparent about his limited coding experience, which is honest but also means he may not fully grasp the technical nuances. The video does not engage with any critical perspectives or potential limitations of the tool, which would have enhanced its rigor.

204 words

Title / Content Match

The title accurately reflects the content: the creator, a non-coder, tests ChatGPT Codex and demonstrates its capabilities in creating an application.

Quality & Reliability

7/10

The video is a practical tutorial with clear demonstrations and step-by-step instructions. The creator is transparent about his limited coding background, which adds authenticity. However, the content is largely promotional and lacks in-depth technical analysis or independent verification of claims.

Chapters

Cited Sources

  • Introducing Codex — Official OpenAI announcement of Codex, referenced as the source of the tool.
  • GitHub — Platform used for repository hosting and integration with Codex.

Concurring Sources

  • Introducing Codex — The official announcement aligns with the video's claims about Codex's features and capabilities.

External References

Contribution & Novelties

The video’s main contribution is its practical demonstration of using ChatGPT Codex as a non-coder, showing a complete workflow from idea to deployed app. It bridges the gap between no-code tools and AI-assisted development, making the concept accessible to a broader audience. The analogy of Codex as a ‘senior developer’ and no-code tools as ‘interns’ is a useful mental model.

Pour aller plus loin :

  • Vibe coding — A term describing the practice of using AI to generate code from natural language, directly relevant to the video’s theme.
  • GitHub Actions — A CI/CD tool that can automate workflows, complementing Codex’s capabilities.
  • OpenAI Codex — The predecessor to ChatGPT Codex, providing historical context.

112 words

Radar Profile

The radar profile shows a balanced performance across all dimensions, with slightly higher scores in information quantity and technical level, reflecting the tutorial's practical nature. The lower score in information quality and reliability suggests that while the content is useful, it lacks depth and critical analysis.

Reliability 6/10

💬 Très positif. Sur les 30 commentaires analysés, les spectateurs expriment une grande satisfaction et gratitude, saluant la clarté de l'explication et l'accessibilité pour les non-développeurs, avec quelques demandes de tutoriels plus approfondis.