Ter info - Wat we leerden van een jaar bouwen met LLM's (Deel I)

[EricGT]

What We Learned from a Year of Building with LLMs (Part I)

Have not finished reading this but after a few minutes found most of it to be true and of value, even a few new surprises

When using structured input, be aware that each LLM family has their own preferences. Claude prefers xml while GPT favors Markdown and JSON.