iiinova — where your digital self keeps evolving

Dr Juulia Suvilehto

@juulia.bsky.social

257 followers 471 following 88 posts

Your friendly neighbourhood (data & neuro-) scientist. Interested in healthcare, big data, social interaction, tea, and cats. 🇫🇮 living in 🇸🇪

Posts Replies Media

Dr Juulia Suvilehto @juulia.bsky.social · 22/10/2025

Great talk by @hollycummins.com at Lindholmen developer day. As a data person and as someone who used to work with healthcare this resonated a lot: "don't make human tell computer things the computer already knows". It is so key but so often neglected in practice (&definitely a thief of joy) #databs

A photo of a woman in front of a large presentation. On the slide she's presenting, it says
The new paradigms
Joy has business value
Get rid of dumb work
If you can't get rid of the work, make computers do the work
Don't make humans tell the computer things the computer already knows
Get rid of flab from the programming model
Measure the important metric, not the one that's easy to measure

073

Dr Juulia Suvilehto @juulia.bsky.social · 08/10/2025

Thank you everyone for your suggestions! This is how I ended up plotting my LLM system output vs human annotation vs LLM-as-a-judge evals. Extra thanks to @libbyheeren.bsky.social for boosting my original question. #databs #dataviz

Four bar plots arranged like a confusion matrix. Bars have two colors stacked, based on evaluator output. Plot shows that the evaluator (DSPy optimized + got-5-nano) flags many false positives and false negatives and does not flag that many true positives or true negatives.

A barplot with three series of two bars each. The series are different evaluation frameworks: Phoenix, deepeval, and DSPy. Of the pairs of bars, the left one displays evaluation output when original rating was incorrect and the right one displays evaluation output when original rating was correct. The color of the bar shows evaluator output. The plot shows that DSPy (non optimized) performs best, ie tags most incorrect responses and does not tag many correct responses.

130

Dr Juulia Suvilehto @juulia.bsky.social · 20/03/2025

This is the mental image that spurred this investigation. I don't think this is what they mean when they say that the trunk is armoured, but this is what I see in my mind's eye

020

Dr Juulia Suvilehto @juulia.bsky.social · 20/03/2025

My first #tidytuesday #pydytuesday where I look at how different palmtree species are armoured. I challenged myself to work in plotnine and it's been a learning curve for sure! Code available here github.com/jtsuvile/tid...

2112