Emergence vs. Scaling

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-creators-emergence-vs-scaling

1. What is the core idea behind "Emergence vs. Scaling"?

   1. Some capabilities grow smoothly with scale. Others seem to appear out of nowhere. Telling them apart is a whole research program. The Big Question Is AI capability a smooth climb or a staircase?
   2. Large-scale pretraining builds general-purpose features
   3. You can describe the limits in one paragraph
   4. multimodal

2. Which term best describes a foundational idea in "Emergence vs. Scaling"?

   1. scaling law
   2. emergence
   3. phase transition
   4. metric effect

3. A learner studying Emergence vs. Scaling would need to understand which concept?

   1. emergence
   2. phase transition
   3. scaling law
   4. metric effect

4. Which of these is directly relevant to Emergence vs. Scaling?

   1. emergence
   2. scaling law
   3. metric effect
   4. phase transition

5. Which of the following is a key point about Emergence vs. Scaling?

   1. Report both strict and partial-credit scores when possible
   2. Sample densely around suspected transition points (compute, parameters)
   3. Use continuous metrics (log-likelihood) alongside discrete (accuracy)
   4. Probe for capability before release, not after scale-up

6. Which of these does NOT belong in a discussion of Emergence vs. Scaling?

   1. Sample densely around suspected transition points (compute, parameters)
   2. Use continuous metrics (log-likelihood) alongside discrete (accuracy)
   3. Large-scale pretraining builds general-purpose features
   4. Report both strict and partial-credit scores when possible

7. What is the key insight about "Why this is not settled" in the context of Emergence vs. Scaling?

   1. Large-scale pretraining builds general-purpose features
   2. You can describe the limits in one paragraph
   3. Both sides have evidence. Specific reasoning tasks clearly show sharp transitions.
   4. multimodal

8. What is the key insight about "The policy stakes" in the context of Emergence vs. Scaling?

   1. Large-scale pretraining builds general-purpose features
   2. You can describe the limits in one paragraph
   3. multimodal
   4. If emergence is real, frontier labs need to test before training larger models.

9. What is the recommended tip about "Ground your practice in fundamentals" in the context of Emergence vs. Scaling?

   1. Every AI capability has an underlying mechanism. Understanding that mechanism tells you where it'll fail — which is more…
   2. Large-scale pretraining builds general-purpose features
   3. You can describe the limits in one paragraph
   4. multimodal

10. Which statement accurately describes an aspect of Emergence vs. Scaling?

    1. Large-scale pretraining builds general-purpose features
    2. Is AI capability a smooth climb or a staircase? The answer is probably 'both, depending on how you measure.
    3. You can describe the limits in one paragraph
    4. multimodal

11. What does working with Emergence vs. Scaling typically involve?

    1. Large-scale pretraining builds general-purpose features
    2. You can describe the limits in one paragraph
    3. Wei et al. (2022) catalogued capabilities that appeared to 'emerge' at particular scales — arithmetic, instruction following, in-context lea…
    4. multimodal

12. Which of the following is true about Emergence vs. Scaling?

    1. Large-scale pretraining builds general-purpose features
    2. You can describe the limits in one paragraph
    3. multimodal
    4. Schaeffer, Miranda, and Koyejo (2023) argued that many emergent abilities are a function of the metric, not the model.

13. Which best describes the scope of "Emergence vs. Scaling"?

    1. It focuses on Some capabilities grow smoothly with scale. Others seem to appear out of nowhere. Telling them apart
    2. It is unrelated to foundations workflows
    3. It applies only to the opposite beginner tier
    4. It was deprecated in 2024 and no longer relevant

14. Which section heading best belongs in a lesson about Emergence vs. Scaling?

    1. Large-scale pretraining builds general-purpose features
    2. The emergence camp
    3. You can describe the limits in one paragraph
    4. multimodal

15. Which section heading best belongs in a lesson about Emergence vs. Scaling?

    1. Large-scale pretraining builds general-purpose features
    2. You can describe the limits in one paragraph
    3. The mirage counter-argument
    4. multimodal