Prompt engineering guidance from Anthropic and OpenAI differs, with Anthropic recommending XML tags and OpenAI favoring Markdown headings. This distinction arises because language models do not parse prompts like code; instead, the effectiveness of delimiters is learned from training data. The choice of delimiter impacts token cost, as XML tags can consume more tokens than Markdown headings, making the latter more economical for frequent prompts. AI
IMPACT Highlights how prompt structure influences model behavior and token costs, impacting efficiency for AI operators.
RANK_REASON The item discusses prompt engineering best practices and differences between two major AI labs, offering analysis rather than a new release or event.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
