T2-R2 quiz
What does next-token training guarantee? Answer: A continuation scored from training. Training predicts tokens.
What is few-shot prompting, at learning depth? Answer: Examples in the prompt. The GPT-3 paper is the usual citation for the idea.
When is a smooth answer evidence? Answer: When a source you can open contains it. Fluency is not a citation.
Sources and go deeper
- Brown and co-authors, Language Models are Few-Shot Learners, 2020 paper last checked 2026-10
- Vaswani and co-authors, Attention Is All You Need, 2017 paper last checked 2026-10
- Large language model — Wikipedia wikipedia last checked 2026-10
- Attention Is All You Need — Wikipedia wikipedia last checked 2026-10