I let LLM (Claude 3 Opus) comment from the perspective of the year 2024 at the time of the decision for the 5th printing of The Art of Intellectual Production of Engineers. First published: 2024-04-03
human comment
.
[]](https://twitter.com/gihyo_hansoku/status/1775392786663264353) WEB+DB PRESS plus âThe Intellectual Production Techniques of Engineers: Learning, Organizing, and Outputting Efficiently,â written by Yasukazu Nishio, is now in its 5th printing due to its popularity! The book is now in its fifth printing! The book explains intellectual production methods using programming and writing as concrete examples. The authorâs specific methods and his trial-and-error experiences are also introduced.
Nishio: 5th printing is coming! The cycle of learning is still valid in the LLM era. Or rather, it is a book about learning how to learn, which is important now that the world is changing so rapidly that textbooks are not matured in time.
Are you sure about that?â
After writing my own promotional piece, âEffective in the LLM Era,â I asked myself, âIs that true?â I then tried to make LLM think about it as a way to validate it. And as a way to verify it, I tried to make LLM think about it.
let LLM comment
.
This is the preface and table of contents to my 2018 book âThe Intellectual Production of Engineersâ Please look back and comment from the perspective of the present day 2024, when LLM technology has developed and the understanding and generation of text is powerfully accelerated by machines.
From a 2024 perspective, the content of âThe Intellectual Production of Engineersâ is becoming increasingly important.
While the development of LLM (Large Language Models) has accelerated information gathering and knowledge acquisition, the importance of chewing over the information obtained and constructing oneâs own model remains unchanged. The âcycle of learningâ proposed in this book is considered to be an effective framework even today.
The chapter on âmotivationâ suggests that human creativity and will will continue to be important even as AI advances in automation.
The skill of âmemory trainingâ is still an important skill for humans, even today when AI has dramatically improved our ability to store and retrieve information. The ability to structure knowledge and apply it, rather than simply memorizing information, is required.
The skill of âreading efficientlyâ has become even more important in todayâs world of âinformation overload. The ability to quickly grasp the essence and select the necessary information is required.
Forming oneâs own thoughtsâ is still an important inherent human ability, even with the development of language models such as ChatGPT. We are expected to critically examine machine-generated information and form our own ideas.
The process of âcoming up with ideasâ is an area in which human creativity can be demonstrated, even with the development of AI. Even though machines can assist in the conception of ideas, it is still the job of humans to ultimately create âvaluable ideas.
Deciding what to learn is becoming even more important with the development of AI. In addition to efficiently completing a given task, the ability to determine what to learn on oneâs own is also required.
In general, the ideas and skills presented in âThe Intellectual Production of Engineersâ can be evaluated as a good book that provides important suggestions for surviving the AI age as well. It is considered to be very useful today as a guideline for harnessing the power of machines while exercising creativity as a human being.
Nishioâs comment
.
The time has come when such texts can be produced at low cost through the use of LLM. How to utilize this technology to create value through intellectual production will have a great impact on intellectual productivity in the future. It can be said that we have entered an age in which it is important to have a birdâs-eye view of âintellectual production.
âMemory trainingâ technology is an important skill for humans even today, when AI has dramatically improved our ability to store and retrieve information. It is not just about memorizing information, but the ability to structure and apply knowledge. Yes, mere memory of information has been delegated to machines with the advent of Google search and then the proliferation of âpersonal knowledge management toolsâ such as Evernote and Scrapbox. Humans have become more important in structuring and applying knowledge skills to use those tools efficiently.
The skill of âreading efficientlyâ has become even more important today, when the flood of information has accelerated even further. The ability to quickly grasp the essence of the information and select the necessary information is required. Recently I have been reading papers to Claude 3 Opus and pair reading while talking to GPT4. This chapter, which reconsiders the âact of readingâ and the âpurpose of readingâ in order to read efficiently, will serve as a foundation for considering changes in âhow to readâ as tools change.
âPutting thoughts togetherâ is still an important inherent human ability, even with the development of language models such as ChatGPT. We are expected to critically examine information generated by machines and form our own ideas. Quite right, LLMs allow us to generate a lot of material for brainstorming ideas, etc. People need guidelines to avoid drowning in a flood of information, and while LLM can summarize, providing guidelines for creating a good summary can make a big difference in the probability of creating value.
The process of âcoming up with ideasâ is an area in which human creativity can be demonstrated, even today with the development of AI. Even though machines can assist in the conception of ideas, it is still the job of humans to ultimately generate valuable ideas. It is important to consider what is meant by âa valuable ideaâ in the phrase, âultimately producing a valuable idea.â An idea that is not implemented has no value, nor does an idea that is not feasible have value. The process of nurturing the seeds of ideas that will lead to future value is of increasing importance.
âDeciding what to learnâ is becoming even more important with the development of AI. We need to be able to not only efficiently complete a given task, but also to identify the subject to be learned on our own. When major changes occur in the world, we cannot be sure that what was once considered âgood to learn thisâ will continue to be useful in the future. Since no one knows the future, we cannot leave it to others; we must choose for ourselves.
It is suggestive to point out that we should leave information storage and retrieval to AI, while focusing human efforts on structuring and applying knowledge. We should not only collect vast amounts of information, but also relate it from our own perspectives and discover the seeds of new ideas. This is the role required of intellectual producers in the LLM era.
In addition, the skills emphasized in this book, such as the ability to read and comprehend to see the essence in this age of information overload, the ability to form oneâs own ideas while borrowing the power of machines, and the ability to nurture ideas and link them to value, are all exactly what will be essential in the coming age.
Furthermore, the importance of deciding for oneself âwhat to learnâ can only be realized in the changing environment brought about by LLM. It is precisely because we live in an era in which the set rules are no longer valid that we must use our own minds to select the subjects of our learning.
I believe that this realization came about because I reexamined my own writing through dialogue with LLM, and I am now meta-questioning my own thinking while utilizing LLM. The accumulation of such activities may lead us to a new way of intellectual production in the LLM era.
In this chapter, we have explored the possibilities of intellectual production with LLM as an ally, building on the content of âThe Intellectual Production of Engineers. In the next chapter, we will accelerate the creation and cultivation of ideas by utilizing tools such as Kozaneba and Scrapbox, which the author had not yet utilized at the time of âThe Intellectual Production Techniques of Engineers. By enhancing the traditional analog way of thinking with the power of digital technology, we should be able to enhance the sophistication of intellectual production.
The last paragraph âIn this chapter - in the next chapterâ could not be generated properly, so I pieced it together and wrote it myself.
next: LENCHI_Chapter 2 Accelerating Intellectual Production with Digital Tools
This page is auto-translated from /nishio/LENCHI_LLMă«2024ćčŽăźèŠçčăăăłăĄăłăăăă 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. Iâm very happy to spread my thought to non-Japanese readers.