from /villagepump/2023/08/12 Putting AI in Scrapbox was too much fun. - Co-operation with AI
- something amazing
- Pretending to interact with AI.
さんの内なる対話による文章なので、暗黙のコンテキストが多く理解が難しい文章になっているように見える
- It seems to me that that’s okay.
- I mean, how can you do that…
- It looks like you’re trying to get the whole picture by tracing the outlines, rather than building up a theory through writing.
- Facing the Black Box
- I don’t think there’s an implicit context, since the final text was purged by ChatGPT as a blog post for the general public, and then I read it and supplemented with commentary…
- As for the exchange in the middle, well, “antivulnerability” refers to Taleb and “collaboration” refers to Ikujiro Nonaka - handles that point to specific concepts.
- simply
がそれらのハンドルを理解していないだけか・・
- By the way, I just tried it, and even with GPT4, I got a “antivulnerability 」や「 collaboration 」をまともに説明できなかった
- ラバーダック・デバッグ的なことが起きてうまくいっている可能性？
- Well, this is an exaggeration, but it’s a hairy question to ask yourself.
- (Read ↓) This is my mistake, OMNI is reading those concepts and conversing with them.
- Since OMNI reads and responds to my Scrapbox
- /nishio/anti-fragility.
- [/nishio/SECI model](https://scrapbox.io/nishio/SECI model).
- I’m talking “read up” on these areas.
- What makes it different from talking to a human is that the omni really does read every page of my Scrapbox.
- I was going to write that it can be done and recalled, but that feature has not been implemented yet, soon.
This page is auto-translated from /nishio/Re:AIとの共同化 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.