Kristina Making a Migraine Tracker with AI

I think it might just be another kind of headache she's made, ...


My comment:

I'm glad you could do this, but I just wish the ordinary calendar app on your phone could do it. A tracker is just an interface and a tagged data type in the events (headache, cake, sunny day etc.). Lot's of people need different interfaces to their calendars for lots of different reasons, and if it was really a calendar app it would let you do this, but the calendar app is not that, it's just one tiny part of what a calendar could be. The problem is that the AI probably wrote a brand new calendar data format and keeps separate database, etc, etc, [but maybe not: see Android Calendar Provider API] and the other problem is that it probably wrote a whole lot of Java/Kotlin whatever and when something changes or you want to change the app what do you do? Next time you want to use AI to modify the program it may be more difficult because you have to tell the AI about what the last AI did and what you want to change. But please do another video in a year or so and let us know what happened, maybe they will have figured out a way to do this, because a lot of people are generating a lot of code using AI and they're all going to want to maintain and change it, so surely there'll be a big market for AI tokens to do that, ... and that is really what I think is the AI business model.

And what is the right way to do this? I think it is to specify the ideas in abstract form. So we have a notion of a calendar provider and a calendar updater, and what we are doing is hooking up a certain type of user-interface widget to a calendar updater and a certain type of calendar provider (i.e. a database). Then  tracker is a collection of calendar updater widgets and a collection of reporting/analysis sources which are lists of events in some format. Then the question comes about how you want to use this provided data. You may elect to be part of a migraine study being conducted by some research programme and then they might ask you to track your consumption of coffee, chocolate etc. Then you should be able to add coffee/chocolate trackers and provide some statistical data, which might only be a rank correlation index over various periods, to their programme. Whatever it is, if you start the process at the top, then you can defer the choice of how to implement it and whether you do that using an AI chatbot or whether you use a formally specified implementation language (see Sukyoung Ryu - Programming Language Research for Technical and Social Good) doesn't really matter because you ought to be able to switch between them using the same abstract specification. See Sixteenth RacketCon in Oakland, CA.

She did a great video about the Poincaré sphere:

Try it out on Spin of Photons: Nature of Polarisation by Shinichi Saito.

Subscribe to Vektorfeld. 

Comments

Post a Comment

Popular posts from this blog

How Could One Unify CMU and MIT

Image
I mean, how to get the best of the two different philosophies of computation. One is based on typed programming languages and the other on engineering with diagrams . This is about practical computing and the cost and feasibility of software development in general. Here is the problem: We have a lot of algorithms which can all be described abstractly using some sort of pseudocode, or perhaps using some particular language (usually Python!). These algorithms are often well-studied and a lot is known about them in terms of their computational complexity in time and space. Substantive practical software systems invariably employ many such algorithms, often implemented in libraries with more or less well-specified APIs. But very few of these libraries are capable of interoperating because they are either packages written in some specific programming language like Java or Haskell, say, or they are written in C and used as object code, or they are written in an interpreted language like Sc...
Read more

Tensor Fields and Simplicial Complexes

Image
Listening to Freya Holmér last night I started to get glimmers of an idea I had long ago about how to represent vector spaces in computational processes using this recursive abstract type :  abstype 'a point = POINT   of {getx :  'a vector,       diff :  'a point -> 'a point,       move :  'a point -> 'a point,       scale : 'a -> 'a point,       proj :  'a point -> 'a} with    fun new i (op +) (op -) (op * ) dot =    let fun self x =  POINT       {getx = x,        move = fn (POINT pr) =>           (self (x + (#getx pr))),        diff = fn (POINT pr) =>          self (x - (#getx pr)),        scale = fn i =>          (self (x * i)),        proj = fn (POINT pr) =>     ...
Read more

HTML in Blog Posts

Just testing stuff: SVG You can click on the blue circle: MathML There is not much you can do with this. See Mathematical Markup Language 1.01 Specification   7.1.5 Mixing and Linking MathML and HTML . It's the big problem  of how you compose languages.   a x 2 + b x + c = 0 You can click on the discriminant: x = − b ± b 2 − 4 ⁢ a ⁢ c 2 ⁢ a 2D Canvas Sound  Beep! WebGPU Next level Parser expression grammar compiler:  https://peggyjs.org/online.html Devine Lu Linvega's unxtal assembler/debugger:  https://wiki.xxi...
Read more