When does adding more instructions to a prompt start to HURT rather than help?

Name a 2026 task where an encoder-decoder transformer still beats a decoder-only LLM

You're prompting GPT-5.5 for English-to-Spanish translation. The zero-shot version works fine. When would adding few-shot examples reliably outperform the zero-shot prompt?

Your prompt iteration has plateaued. Walk through the decision of whether to fine-tune or invest in further prompt engineering, with explicit signals for each path.

Flashcard: what is the ReAct prompting pattern?