jlengelbrecht

No but the project has undergone an in depth evaluation from Open Collective prior to being accepted for fiscal hosting. Additionally I am in contact with an Attorney who is reviewing the projects stance. The project as it is right now is aims to not cross any boundaries that would make it a medical device. The platform does not control insulin or make dosing recommendations. It's still in early alpha but I have made my position clear. The platform serves as a tool to help you understand your data and help you have better discussions with your medical provider.

Thank you. Really appreciate this feedback. I am actually already thinking about this. Hallucinations need to be clearly called out which is important. This is on the project's roadmap for me to address. There needs to be a way for users to clearly say "This is wrong. you need to reevaluate" In terms of alerting this is where we drift from what the LLM does and what the platform does. The platform already ingests data and stores it in the RAG system which provides the AI context but AI is the component that used for chatting about your data and providing you daily briefs. Alerting lives on the platform side so the AI may use it when we start implementing pattern detection to alert diabetics and care takers with questions such as "I see your glucose is rising. Did you eat and not bolus?" but for actual glucose events that fire during hyper or hypo events this is hard coded in the platform itself.

Really appreciate this feedback. Every failure you named is real. I have had similar experiences with ChatGPT giving me bad information. I plan on solving for this by expanding on the RAG system that's being used. The AI gets its context based on settings you are giving it. The platform has some settings built in around insulin types but this needs to be expanded. The platform is not designed to give you dosing recommendations I really built this to help you understand your own data so you don't fly blind. Any thing the AI says to you is clearly labeled as not medical advice and the expectation is that your medical provider is in the loop before you make any medical decisions. I will take your feedback into consideration as I continue to explore new ways to shape the output you get from the platform.

Yes this is actually on the roadmap. The project does not do this today as its still in alapha but what you are describing is exactly what i am building toward. Specifically behavior analysis where the AI notices changes in your blood glucose and asks you follow up questions to help you understand what you might have missed. I have had early adopters of the project specifically ask for this.

[flagged]

I think vibe coding in general is a risk. I think companies need to stop pursuing no code solutions for production products as AI becomes more prevalent in the day to day. I think its fine for proof of concepts but products need to go in front of engineers before they land in prod. If engineering teams are using AI this is fine so long as there is structure behind it and they understand what the code does and what tools are being called. Frameworks like BMAD has been great at enabling developers adopt spec driven development with AI.

Interesting. Seems like the worlds demand for nuclear is obvious considering the state of oil shipments today.