Hacker News Reader

Comment by surgicalcoder | Hacker News Reader

I'm a T1D who has an insulin pump looping with AndroidAPS and NightScout, what does this give you that Nightscout and Autotune doesn't give you?

And how do you deal with AI hallucinations?

View on HN

I think the only thing that could be made better is tuning the I:C/ISF/Basal values automatically. And ISF is already handled by DynamicISF, while not perfect it reduces the variables you have to tweak.

Otherwise, when tuned correctly, oref1 et.al. provide amazing results and are safe. Hard to understand where I would use LLMs in this.

You sort of have that - not automatically though, but you can run autotune against nightscout and get a report of where things need to be adjusted. I run oref1 with DyanmicISF, and just run autotune every few months just to tweak values.

I genuinely don't see where I would use an LLM in this process.

I agree. For us, who are really good with software and all that, AndroidAPS is really good when you can easily learn how to use it.

Not that great for non-technical people. But it saved my life at least.

Edit: thanks for reminding me about Autotune. I used the azure app ages ago, but it's now integrated in AndroidAPS behind a secret setting.

If your already using AAPS and are happy with it then my honest answer is you don't really need this unless you want to get the data analysis layer. What you would get is AI analysis of your data, daily briefs, alerting, etc. I have written an honest comparison to other OSS tools today. This should provide some clarity on what this is and isn't. Let me know if you have any suggestions or ideas on what would make what I built more useful to you as am AAPS user. Happy to hear how the project can adapt and grow and fit into your usecase. - https://glycemicgpt.org/docs/platform/concepts/relationship-...

Reply on news.ycombinator.com