Effects of thought acceleration in [self-originated LLM

  • I feel like I summarized it, but you didnā€™t?

  • Intellectual Productivity Study Group by LLM and didnā€™t cut it out, Iā€™ll summarize.

  • Comparison of ChatGPT and self-derived omni.

    • from Raw ChatGPT and omni use cases are different.
      • Since most texts in the world are written in ā€œexpressions that many people can read and understandā€, whereas my research notes are written in ā€œexpressions that I can understandā€, an AI that RAGs with the latter accelerates my personal thinking much more efficiently than ChatGPT
      • In my research notes I donā€™t write explanations for words I know, so the AI that reads them doesnā€™t write explanations for what I know either. Concepts are tools for the economy of thought. So it is more efficient to use them without explanation in oneā€™s thinking.
      • It is useful to use ChatGPT when explaining it to others
    • image iceberg model
      • The omniā€™s output is closer to my personal water surface (the boundary of what is not yet verbalized), so it is more effective in supporting verbalization.
      • Maybe it has to do with the different characteristics of blogs and Scrapbox: in Scrapbox, instead of explaining the same concept over and over again, you create a page for that concept and link to it.
    • human.iconI feel that the style of writing is a major factor in the speed of comprehension, and I have the impression that a sentence that is easier for me to read is generated when I give my own sentence to GPT to generate, rather than just having GPT generate the sentence for me.
      • nishio.iconIndeed, it may be that OMNI is easier for me to read because it speaks in my style. In the end, it may be that AI assistants are more productive for each individual if they are personalized to the individual.
  • Comparison of self-derived and stranger-derived omni.

    • Feelings differ depending on whether the data is primarily self-inflicted or not
    • When itā€™s self-originated, itā€™s like AI and humans are driving the thinking as a unified entity.
      • I feel like Iā€™m accelerating.ā€
      • Feel like youā€™re ā€œseeing things from a different perspective.ā€
    • When derived from others, the feeling of ā€œOh, so this is what Mr. X said about this subjectā€¦ā€
      • I feel like I ā€œfound someone elseā€™s statement.ā€
    • Fragments derived from oneself are reconstructed once chewed up inside oneself, so there is a sense of smooth connection. Fragments derived from others still have a hard surface.
    • Fragments of self-derived Different Perspectives drive dialectic development more strongly than fragments of different perspectives derived from others.
      • Is it because Iā€™m naive enough to pass off things of other peopleā€™s origin as ā€œthatā€™s one way of thinkingā€ even if it differs from my current opinion?
      • The ā€œitā€™s normal for others to have different opinionsā€ runaround?
      • If your self-derived opinion differs from your current opinion, since you are both you, ā€œWhy do we disagree?ā€ Since they are both me, does this strongly trigger the question, ā€œWhy do we have different opinions?

This page is auto-translated from /nishio/č‡Ŗ分ē”±ę„LLMć®ę€č€ƒåŠ é€ŸåŠ¹ęžœ 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. Iā€™m very happy to spread my thought to non-Japanese readers.