-
Notifications
You must be signed in to change notification settings - Fork 4
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Image occlusion and always different questionnaire #18
Comments
For your second idea, do you mean the generated questions change depending on what questions were generated previously, and the difficulty changes depending on how many questions you answered correctly? |
Yes, I thought about it like this, if a question that was created was later evaluated and answered well, then in the next session that same question will increase in difficulty. Here I show you a diagram, I hope I express myself well, I am not a programmer. graph TD
A[Create Question] --> B[Deck]
B --> C[Evaluate Question]
C --> D{How did you respond?}
D --> E[Bad or so-so]
E --> F[Remains the same]
F --> C
D --> G[Good]
G --> H{How many times did you answer correctly?}
H --> I[Only once]
H --> J[More than once]
I --> F
J --> K[Increase difficulty of this card only]
K --> A
|
Oh, I see. I think I have a pretty good idea of what you're talking about (the diagram is very helpful). This is a really interesting idea so I'll likely include it as part of the Test Mode feature. |
Great, to clarify further I see that I forgot to add after more than once that said card that has already been answered correctly more than once will return to the deck but in "learned" mode so that it is not shown again, but also not deleted, I will only be able to see it if I unlock it for the final review 😉 |
Hello first of all great plugin, I see that it will incorporate questions based on images and pdf in future versions, so I share my ideas
Use multimodal models to recognize text in images to cover said text automatically, I would like this to be used with the excalidraw plugin so that it is compatible, here is an example of how it can be made simple
Grabacion.2024-10-03.184556.mp4
this is related to testo mode and Question Variety, the idea is that sometimes there are concepts that must be memorized, there is no other way, but on other occasions they must only be understood in their different situations, the clearest example of this is mathematics, providing the LLM as a source the notes or PDFs (and other sources if necessary) so that in each new study session, the exercises are always new and based on this evaluation the next session will be more difficult 🫡
The text was updated successfully, but these errors were encountered: