LES DEVS ARRÊTENT D'UTILISER CLAUDE : c'est de pire en pire...

LES DEVS ARRÊTENT D'UTILISER CLAUDE : c'est de pire en pire...

The developers are stopping using Claude: it's getting worse and worse...

Title history
  • LES DEVS ARRÊTENT D'UTILISER CLAUDE : c'est de pire en pire... — observed on 20261101-0122 UTC (YouTube)

by Melvynx · View the channel on PSI

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 Melvynx 👥 67K 📅 May 14, 2026 ⏱ 22 min 👁 16K 📄 news review 🧭 2026-11-01
Available in: English (current) Français

Keywords

ClaudeCodextoken limitsdeveloper workflowAI pricing

Summary

The video is a vlog-style commentary by developer Melvynx on recent changes to Claude’s pricing and usage limits, which have sparked backlash in the developer community. He explains how Anthropic now caps API credits at $200 per month for Pro plan users, affecting third-party tools that rely on Claude, such as OpenClaw and T3 Code. He shares the angry reaction from community members, especially Théo (creator of T3), who publicly criticized Anthropic and offered donations to open source. Melvynx then details his personal migration from Claude to OpenAI’s Codex, citing better performance, more generous token limits, and lower cost. He demonstrates how to migrate skills and rules from Claude to Codex, and highlights the new Codex app interface. He also discusses his current stack, which includes both Claude and Codex, and recommends Codex for most tasks, while acknowledging Claude remains superior for frontend work. The video concludes with Melvynx urging viewers to try Codex and subscribe to his formation for more details.

162 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides valuable practical insights for developers navigating the rapidly evolving landscape of AI coding assistants. It offers real-world usage data, such as token consumption and cost comparisons between Claude and Codex, and gives concrete migration tips for skills and rules. The argumentation is largely anecdotal, based on personal experience and community reactions, rather than systematic testing or objective benchmarks. Melvynx presents a clear narrative: Anthropic’s pricing changes are unfair and have eroded trust, while OpenAI’s Codex currently offers better value and performance. The reasoning is coherent and relatable, though it lacks evidence from broader studies or official documentation. The strength lies in its firsthand testimony and actionable advice, making it useful for developers considering a switch.

Scientific Rigor, Source Quality, Title Accuracy

The video does not cite external scientific sources; it relies on personal experience and social media reactions. The description links are mostly promotional (courses, boilerplate, etc.) and do not serve as authoritative references. The title is appropriate and reflects the content, though it slightly exaggerates the universality of the trend (‘developers stop using Claude’). While the video mentions specific pricing policies and changes, these are not independently verified, and no official documents are referenced. The rigor is moderate: the presenter is transparent about his own biases and usage, but the overall reliability is limited by the subjective and unofficial nature of the information. The comments reveal a mix of agreement and skepticism, but no additional authoritative sources are introduced.

252 words

Title / Content Match

The title accurately reflects the content: the video discusses the growing dissatisfaction with Claude and the migration of developers to Codex, matching the title's claim.

Quality & Reliability

5/10

The video presents personal opinions, anecdotal evidence, and some usage data, but lacks rigorous scientific sources. It offers practical insights into AI coding tools and pricing changes, but reliability is limited due to subjective bias and lack of independent verification.

Chapters

Cited Sources

Contribution & Novelties

The video contributes an up-to-date, personal perspective on the AI coding tool landscape, specifically the impact of Anthropic’s pricing changes on the developer community. It offers original, practical content on migrating from Claude to Codex, including a detailed walkthrough of transferring skills and rules, which is not commonly covered in official documentation. The author also shares real usage metrics and cost comparisons, adding empirical value to the discussion.

Pour aller plus loin :

  • Anthropic — Company behind Claude; provides context on the business decisions.
  • OpenAI — Developer of Codex and GPT models; relevant for comparing AI providers.
  • Large language model — Background on the underlying technology of AI coding assistants.

110 words

Radar Profile

The radar profile shows high technicality and moderate quantity of information, but low reliability and quality scores, indicating a subjectively informative video that lacks rigorous sourcing.

Reliability 4/10

💬 Balanced: on the 30 comments analysed, many share the migration to Codex and appreciate the practical advice, while others criticize the constant tool switching and remind about economic realities of AI pricing.