The 2020 prompt and the 2026 prompt are not the same artifact
In 2020 a prompt was a few sentences of text fed to a base language model with no chat training, no tool use, no structured output mode. The art was getting it to continue your text in the right voice. "Few-shot learning" was the headline trick because the alternative was nothing.
In 2026 a prompt is the configuration of a complex system: a chat-tuned model with extended thinking, function calling, structured outputs, citation, large context windows, modality routing (vision, audio, files), and built-in safety policies. The prompt sits inside an agent loop that may execute, retry, and self-correct. The same words mean different things to different generations of model.
What changed, in order of impact
- Instruction-tuning — the model now expects to be talked to, not continued.
- Tool use — "call this function" is now a primitive verb.
- Structured outputs — "return JSON matching this schema" is enforced, not requested.
- Long context — packing 200k tokens of evidence is normal.
- Reasoning modes — Claude's extended thinking, OpenAI's o-series, Gemini's thinking — all change how prompts are read.
- Multimodality — images, audio, files arrive alongside text.
Why old advice misleads
Most prompt-engineering tips written before 2024 are about coaxing capability out of small base models. They tell you to add "think step by step," use elaborate roleplay, or chain-of-thought everything. On a 2026 frontier model some of that is unnecessary, some is harmful (it consumes thinking budget on trivial tasks), and some has been replaced by structured features (tools, schemas, reasoning modes). Read prompt advice with a date in mind.
Ko/En 모드 둘 다 제공해주셔서 잘 활용하고 있습니다 :) "prompt advice 읽을 때 날짜 머리에 두고 봐" 부분이 한국어로만 봤을 때는 한 번에 와닿지 않았는데, En 모드로 바꿔서 보니 의미가 분명해지더라고요. 혹시 같은 부분에서 갸우뚱하실 분들 계실까 해서 공유드려요! 항상 감사합니다 ^^