Have you tried applying to AWS Activate? I'm not sure whether they support non-profits, but if you can swing it, they'll subsidise your compute and some model costs.
In terms of a budget friendly alternatives, definitely look into fly.io. We have a AWS setup, but run some compute for ephemeral use cases in fly.io.
> Also, if anyone has experience with applying spaced repetition or other memorization techniques to chatbot interfaces and long-form text retention, I'd love to hear your thoughts.
Have some experience with conversational experiences and LLMs. It all depends on what the modality of the interaction is. Is it something that users can have a long chat conversation with? Or is it more like the anki experience where "flashcards" get presented to you?
I'm currently building a hybrid experience where users can have long conversations for things like conversation practice, while the bot also having the ability to present Anki-style flashcards. I'm also exploring other modalities for "cards" such as questions that would allow the user to respond to the bot's question with a voice message, and having the system analyze the recording for pronunciation/tone issues. Weaving these multiple modalities into a seamless experience is something that I'm still working on.
In terms of a budget friendly alternatives, definitely look into fly.io. We have a AWS setup, but run some compute for ephemeral use cases in fly.io.
> Also, if anyone has experience with applying spaced repetition or other memorization techniques to chatbot interfaces and long-form text retention, I'd love to hear your thoughts.
Have some experience with conversational experiences and LLMs. It all depends on what the modality of the interaction is. Is it something that users can have a long chat conversation with? Or is it more like the anki experience where "flashcards" get presented to you?