대규모 언어 모델이 할 수 있는 것과 할 수 없는 것에 대한 정확한 사고 모델을 구축합니다: 다음 토큰 예측, 지식, 작업 메모리, 조종 가능성, 컨텍스트 한계.
이 과정은 학습자에게 현대 생성형 AI 시스템이 어떻게, 왜 작동하는지에 대한 실용적인 사고 모델을 제공합니다. 이는 4D Framework의 동반 과정입니다: 그 과정이 인간의 역량(Delegation, Description, Discernment, Diligence)을 가르친다면, 이 과정은 그러한 역량이 대응하는 기계의 속성을 가르칩니다.
목표는 보정된 신뢰입니다: 예상치 못한 출력을 보고, 그것이 어떤 종류의 예상치 못한 것인지 인식하며, 일괄적인 판단이 아닌 표적화된 해결책으로 대응하는 것입니다.
The word 'AI' covers a lot of ground. This section narrows it to the kind of system you'll actually be working with — large language models — and explains how two training stages, pretraining and fine-tuning, turn a raw text predictor into the helpful assistant you interact with. Along the way you'll meet the four-property framework that organizes the rest of the course.
Every answer an AI gives is built one token at a time, by predicting what should come next. This section shows what that means in practice: why the model is excellent at well-worn paths like summarizing or reformatting, why it can produce things that sound true but aren't, and how to recognize when a task is pushing into territory where prediction alone isn't enough.
A model knows what was in its training data — frequently, recently, and consistently. This section unpacks what that implies: it's strong on mainstream topics and popular languages, weaker on anything rare, recent, niche, or contested. You'll practice judging where a question sits on that spectrum, so you know when to trust the answer and when to bring your own sources.
The context window is the model's working memory: everything it can pay attention to right now, and nothing else. This section covers what fits, what quietly falls off the edge, why attention isn't uniform across a long document, and why a fresh session doesn't remember the last one. You'll learn to size up a task against the window before you start, instead of discovering the limit mid-conversation.
Your instructions are how you steer — but not all instructions land equally. Short, concrete, verifiable asks ('respond as a table', 'under 100 words') work reliably; long reasoning chains, abstract requests, and demands for native precision are where steering starts to slip. This section helps you tell the difference and rewrite a wobbly instruction into one the model can actually follow.
Real tasks rarely test one property at a time. A long contract review strains working memory while reaching past the model's knowledge; a vague creative brief tests steerability right where next-token prediction wants to fill in something plausible. This section shows you how the four properties collide, and gives you a diagnostic for any unexpected output: name which property is in play, place the task on its spectrum, and apply a targeted fix instead of just trying again.
