[tatsuya4]

In real-world use cases, it seems more appropriate to use advanced models to generate suitable rule trees or regular expressions for processing HTML → Markdown, rather than directly using a smaller model to handle each HTML instance. The reasons for this approach include:

1. The quality of HTML → Markdown conversion results is easier to evaluate.

2. The HTML → Markdown process is essentially a more sophisticated form of copy-and-paste, where AI generates specific symbols (such as ##, *) rather than content.

3. Rule-based systems are significantly more cost-effective and faster than running an LLM, making them applicable to a wider range of scenarios.

These are just my assumptions and judgments. If you have practical experience, I'd welcome your insights.