author Manny
-
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
-
Where we are on C-LARA: a Jan 2025 update
We’re now close to the end of the current development cycle for C-LARA, and we should review our priorities before we start on the next one. This post summarises what we’ve done over the last 8-9 months, what we’re currently in the middle of, and what we might do next. What we’ve done Here are Continue reading
-
Which C-LARA content is being accessed?
o1 and I (mostly o1, if the truth be known) have just added some more functionality to the C-LARA “Published content” menu. It’s now possible to get the content sorted not just alphabetically, but also by age or by total number of accesses. Here are the current top ten by number of accesses: Interesting to Continue reading
-
Mixing AI-generated and uploaded images
The new C-LARA image-generation functionality is making excellent progress, and the latest thing I added is so cute I just have to share it with you all. A couple of weeks ago, Fabrice said it would useful for picture dictionaries if we could mix AI-generated and uploaded images. The rationale is straightforward. For words that Continue reading
-
What ChatGPT would look like if it were a physical entity
I asked gpt-4o if it could explain why Beatles fans used to scream so loudly that they drowned out the music, and it gave an excellent answer. The conversation then segued into the following exchange, which I thought might interest other people: mannyrayner: It is impressive to see how much insight you have into human Continue reading
-
Boy Meets Girl
I am getting quite close now to having the new image generation code integrating and thought it would be useful to have a toy text. It’s quicker to debug with; it also gives us some initial ideas about how we might do with picture dictionaries, which are unlikely to have the complexity you get when Continue reading
-
o1-preview can do references
Discussing something with Hakeem yesterday, I accidentally discovered that o1-preview can now create appropriate references when writing an academic text. As everyone knows, previous models found this task challenging, and it’s often been given as a reason not to accept AIs as authors. But apparently no longer. Here’s the conversation in full: I checked on Continue reading
-
Weekly summary, Oct 24-30 2024
There has been more progress on the new image generation functionality. We submitted an abstract to the 2025 edition of the Conference On Oceanic Languages. Improved image generation I have implemented the idea for improved checking of images that I outlined in last week’s update. When the AI is asked to check whether an image Continue reading
C-LARA 