#mlforkids — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #mlforkids, aggregated by home.social.
-
I had a look at the server request logs for #MLforKids yesterday and it's probably a sign of my naivety that I was so surprised by the constant level of malicious traffic the site gets.
-
#MLforKids now supports tool calling in language model projects
Students create tools using #Scratch code blocks. Tools auto register with the model, and become available for the model to use.
Tools can get info from the Scratch project, control sprites, use Scratch variables as memory, and more
-
I've added support for tool calling from language models in #MLforKids
Students create tools in #Scratch using normal Scratch code. Tools auto register with the loaded model, and become available for the model to use - to get information from the Scratch project, or control what is happening
-
I'm in Dundee!
That was a ludicrously long journey (I've gone to US cities in less time) but it was a nice chance to relax, read, play some new Switch games, and tinker with a new #MLforKids feature
-
I worked on a bunch of improvements to #MLforKids over Christmas. Last night, I went back and wrote a rambling stream-of-consciousness post about the thinking that went into one of them (addressing error reports from resource constrained browsers)
-
New #MLforKids project! It explains a bit of prompt engineering by making a role prompting game in #Scratch with a language model
https://dalelane.co.uk/blog/?p=5799 -
Students use #Scratch to visualise the performance of different language models (and the impact of temperature and Top-P settings).
Even with the small selection of language models I have on #MLforKids this shows big differences
-
I've written a new #MLforKids worksheet.
This one gives a taster into LLM benchmarks, by getting students to compare how different language models perform with simple addition questions (eg. "What is 12 + 74?")
https://machinelearningforkids.co.uk/#!/worksheets?worksheet=Benchmark
-
Playing with an idea for a possible #MLforKids project. I'm using a language model in #Scratch to repeatedly translate a sentence from English to another language and then back again.
If I do that over and over again, what mistakes are introduced? Is that interesting? Educational?
-
"RAG-time" is a #MLforKids project that introduces how we use language models to answer questions about recent events.
Adding relevant documents to the context transforms the answers the model can give
Step-by-step instructions to create this in #Scratch at https://machinelearningforkids.co.uk/worksheets
-
Experimenting with adding support for simple RAG projects in #Scratch to #MLforKids
Without the context, the model hallucinates with very topical or time-sensitive questions.
With it, I get the right answer! -
Scratch has long been built from many separately developed components. My #MLforKids fork of Scratch includes changes in seven repos.
#Scratch is now (understandably!) migrating to a single mono-repo - so I'm starting to look into migrating my changes.
https://github.com/scratchfoundation/scratch-editor/blob/develop/README.md#monorepo-migration
-
I'm in London for Festival Of Play - a STEM event that uses video games & game dev to motivate and teach kids about computing.
I'll be running AI workshops for primary school kids using #MLforKids (and trying to make it look as fun as video game activities!)
https://www.eventbrite.co.uk/e/festival-of-play-2025-london-tickets-1151717320509
-
I've recorded an explanation of what I was working on for my "vacation" last week - adding generative AI to #MLforKids by introducing language models to #Scratch
As demos go... it... didn't go as planned. But I left the mistakes in, as I figure better that than pretend AI gets everything right!
-
Writing a new #MLforKids worksheet based on creating a voice-controlled calculator
Works well when I do it at home by myself in a quiet room, but not sure how it'd work with lots of students doing it at the same time in a noisy classroom. Something to test with a friendly local school, perhaps!
-
Trying out an idea for a new #MLforKids project - recreating an AI project from the 1960's in #Scratch.
"Shoebox" was a voice-recognition calculator - you can learn about it at https://www.ibm.com/history/voice-recognition
This is my attempt to see if students could recreate it today.
-
Very surprising spike in account creations and logins on #MLforKids on Christmas day - nearly 100,000 visitors!
The site is normally quiet on school holidays... wonder why the bump? Best guess is that some kids got https://machinelearningforkids.co.uk/book for Christmas? (which would be unusual, considering it's a few years old now)
-
Got lots done on #MLforKids this weekend. And if I've done it right, no-one will notice! 🤷♂️
I fixed a few bugs that I've been stuck on for an age, and rebased my fork of Scratch (which I've been putting off all year because of the major changes the Scratch Team have made to how Scratch is built and packaged)
-
A nice example of the sort of #MLforKids project that this enables is training a classifier to predict whether you will like a book based on a picture of the cover (as it makes super easy to bring lots of new book cover images into #scratch)
-
Re-reading this old post last night sent me down a rabbit hole, where I discovered the community has moved on from TFDF. It's been superseded by a new library! 🤦
This morning I've been working on migrating to Yggdrasil Decision Forests (helped by some impressively clear migration docs)
https://ydf.readthedocs.io/en/latest/tutorial/migrating_to_ydf
-
#blog2024revisited I spent my Easter holiday rewriting how #MLforKids creates and uses numbers models, migrating from scikit-learn to #TensorFlow Decision Forests.
In April, I wrote a blog post to walk through how I'm using TFDF, as well as explain the reasons for the rewrite.
-
I figured out how to get SPICE (pitch estimation ML model) running in TensorFlowJS last night, and was so pleased I ended up writing a new #MLforKids worksheet to show it off!
In "Voice Tuner", you get #Scratch to pick a random note and play it for a few seconds. You need to hum or sing that note.
Download the worksheet from https://machinelearningforkids.co.uk/worksheets
-
#blog2024revisited I spent a lot of February half-term adding a new type of #MachineLearning model to #MLforKids : regression models in #Scratch !
Ahead of flipping the go-live switch on this new feature, I wrote a blog post to get some feedback on what I was doing.
-
The simplest #MLforKids project is "Describe the glass"
Students use #Scratch to create a decision tree for whether a glass is "half full" or "half empty"
It's such a helpful introduction to #MachineLearning to start with a model that is so simple they can see exactly what it is doing
-
I love running this #MLforKids project: giving children an intro to using #AI to recognise handwriting.
They train their own #MachineLearning model and use it to sort (virtual) mail in #Scratch.
-
#blog2024revisited In January I wrote about the work I had done on #MLforKids over Christmas 2023: adding an option for students to use their own storage for their machine learning projects instead of storing all projects in the cloud.
It was a cathartic end to what had been a huge piece of work!
-
Most of the work I do on #MLforKids involves adding ML models into #Scratch.
But to help students create interesting projects, I also need to help them get external data into Scratch for training and classifying.
Yesterday, I worked on blocks that let them use books data from OpenLibrary.
-
Teach kids about #machinelearning by making a AI-powered basketball game in #Scratch
Train a simple regression model to shoot hoops
More info, and a link to full #MLforKids instructions:
https://dalelane.co.uk/blog/?p=5200 -
I've written a new #MLforKids worksheet - this time around training a regression model to shoot basketballs into a hoop.
I realise I'm biased, but I think creating the training examples for this one is a legitimately fun game in its own right 😜
-
Teach kids about #machinelearning by making a AI-powered Space Invaders game in #Scratch
Train a regression model to choose the direction to fire the ball
More info, and a link to full #MLforKids instructions:
https://dalelane.co.uk/blog/?p=5181