C-LARA

An AI collaborates with humans to build a language learning app.


February 2025

  • Weekly report, Feb 13-19 2025

    Over the last week, we’ve been focussing on two things: images, which are now starting to work quite well, and the beginnings of our ambitious project to refactor the code-base so that the AI can understand it better. Images Sophie has been using the image-generation functionality a great deal over the last few weeks to… Continue reading

  • Using Deep Seek in C-LARA

    I have been consulting the Deep Seek API documentation, and it seems very easy to arrange things so that C-LARA can be given an option to use Deep Seek models as well as OpenAI ones. They claim to have done the sensible thing and made their API fully OpenAI-compatible. Here’s the basic call: Just one… Continue reading

  • o3-mini now available in C-LARA

    I have added support for OpenAI’s newly released o3-mini model in C-LARA. You select it from the “Edit Configuration Information” screen, accessible from the far right of the top-level menu: So far, it’s not clear how useful it is for the kinds of things we do on the C-LARA platform – the main focus has… Continue reading