Hacker News Reader

Comment by lambda | Hacker News Reader

Can you provide some references to the research you're referring to? Sounds interesting but you haven't really provided enough information to find it.

View on HN

That is the point – you can't just provide the references in a short post here.

You need much more time and guidance.

Ironically, LLMs are pretty good at finding stuff like that from vague descriptions. With that, I think the parent commenter meant Art Graesser's AutoTutor work based on the terminology used (hint/pump).

TLDR: Actual human tutoring sessions were recorded and analyzed and Socratic questioning was barely used at all. Instead the following pattern was observed:

Pump — "Uh huh?" "What else?" Costs nothing, so try it first.

Hint — points at the region of the answer. "What about the pumpkin's motion sideways?"

Prompt — fishes for one specific word, with the sentence frame supplied. "The pumpkin keeps moving forward at the same ___?"

Assertion — just says it. "It keeps the runner's horizontal velocity."

Yes, you're on the money. And this is a perfect example of how people should use llms. Use them to deepen your own research and understanding rather than use them to glaze and implement the first naive idea that comes into your head (or the first idea they suggest as a response to a vague prompt, which typically is substantially worse than if you get them into the right vector space using jargon)

Reply on news.ycombinator.com