Embedded AI is starting to appear in open source AID systems, offered as copy and paste, bring your own key, or a service the project runs. A year of measuring these models says the clinical risk is much the same in all three. The regulatory position is not, and the intuition about which is safest runs backwards.
Ask once and you get an answer. Ask fifty times and you get eighteen different pairs of safety limits, a headline that flips one time in five, and an app that accepts them all. Inside the £4.49 app that turns your diabetes data into chatbot advice on your OS-AID settings.
A slightly rhetorical question, I’ll admit, but a pertinent one. Once again, I have been trying out the latest (read most heavily pushed on Facebook […]
We took Nightscout data from three people and gave it to 5 Large Language Models with a detailed prompt to see how they would respond.
The results weren’t what I was expecting.
Ask ChatGPT to estimate the carbs in your lunch. Now ask it again. And again. Five hundred times. You’d expect the same answer each time. […]
Here we discuss the LLMs design and purpose in the context of interacting with and advising on health data, and demonstrate why the two may be at odds with one another:
https://wp.me/p7O2EL-2BM
In this final section of the “In conversation with” experiment, we provided “access” to complete Nightscout data for the LLM models.
Unfortunately, this is also where the wheels rather fell off, and whilst the results gave an initial appearance of credibility, upon further investigation it became clear that what was presented was rather less then effective and could have been very unsafe.
Read on to learn more: https://wp.me/p7O2EL-2BE
In this article, we look at the abilities of the LLMs to review data charts in image form from Nightscout and see what they suggest in terms of changing treatments, and how the contextualise those changes.
As a key way that users are interacting with these models, this is a critical insight into what you might get.
It’s a big read with lots to go through, but we’d highly recommend taking the time. It revealed a lot of unexpected items that are potential gotchas…
In the dynamic world of diabetes management, anything that can help us accurately estimate carbohydrates in our meals is a game-changer. Imagine a future where […]
As I stated in the last “In conversation with” article, I split the questions into three sets. Factual, picture analysis and data analysis. This is […]
Copyright © 2026 | WordPress Theme by MH Themes