Abstract and let the LLM solve it, then pull it back.
abstraction and let LLM solve then pull back.
tokoroten the question of why a good diagram is created after writing a book.
https://gyazo.com/604693c4a3409b054601396876aff2eb
tokoroten Well, I was reading the math guidelines and I found a very good diagram, so I'm just quoting it.
https://gyazo.com/b848a9097f6f5c3d6aedc9814e50adae
nishio I don't think this cycle is PDCA or SECI, but I wonder if it has a name.
tokoroten In case you're wondering, this is what it says in the math teaching guidelines, but it doesn't have a name!
[Mathematics Courses of Study for Junior High Schools (Notification in 2017) Commentary (PDF) https://www.mext.go.jp/component/a_menu/education/micro_detail/__icsFiles/afieldfile/2019/03/18/ 1387018_004.pdf]
https://gyazo.com/7437c0650ce551b78fcca507b299f23d
tokoroten If I may ask, modeling simulation?
kawahiii It's hard to use because it's hard to understand the meaning, but I think "cycle diagram of mathematical activities" is close to the official name, just in case.
It's hard to read from the guidelines, but in "[Summary of Discussions in the Working Group on Arithmetic and Mathematics (PDF) https://www.mext.go.jp/b_menu/shingi/chukyo/chukyo3/073/sonota/__icsFiles/ afieldfile/2016/09/12/1376993.pdf]". (Guidance notes are made from the WG)
By the way, some people in the arithmetic-mathematical community call it "a circular diagram of mathematical activities" or something like that. w
https://gyazo.com/390148eb259a98e1240bedae5eaf3c59
https://gyazo.com/7a0f465e9ec034dcc0814aabd57977b3
tokoroten Finally got around to reading the original!
Thank you.
kawahiii Good to hear!
The original was probably first published in WG #2 on January 22, 2016, so it looks like it was refined from there and became the final guideline form. It seems to have been refined from here to the final form of the Courses of Study.
https://gyazo.com/772995976ee7cd33e9d0def8b9bb9594
nishio Excellent! Thank you very much! I'll add it to the summary later!
relevance
アナロジー.icon
analogy
メタファー空間でGPT4に発散と抽象化をさせてから具体化する.icon
Divergence and abstraction in GPT4 in metaphor space and then concretization.
digression
tokoroten I wrote a book like this
In case you're wondering, there is a column in the book called "ChatGPT, Abstract and Concrete," and it talks about it in text, but it didn't make such a nice diagram.
That was a waste of time.
ChatGPT Strategy
tokoroten The column in question contains sentences like this.
https://pbs.twimg.com/media/F4rv5d9bEAEOU11?format=png&name=900x900#.png
tokoroten By the way, in the column in question, when I wrote "The reason why Todai students are excellent is not only because they are excellent, but also because their friends are also excellent", it was edited out. I wrote "The reason why Todai students are excellent is not only because they are excellent, but also because their friends are also excellent.
X is excellent because his friends are also excellent.
---
This page is auto-translated from /nishio/抽象化してLLMに解かせてから引き戻す using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.