[fao_]

> agentic AI

Yeah I don't want LLMs near anything life or death, where a hallucination can kill, thank you very much.

[DGrechko]

Agree with you on that, it was my concern too, but the way I think about it is access to information, the goal is not to provide hallucinations with a straight face (aka GPT), but rather use it as a way to extract necessary information fast. For instance, I have a built-in RAG that reads of growing collection on books on medical, survival, etc. (https://github.com/dmitry-grechko/waycore-knowledge) that AI agent is using to answer questions. Moreover, it has a built-in safety loop to always inform users on the accuracy of the information, but also if the information request has an impact on health & safety, it will warn users about it too.

So, I certainly see the inherited risk and problems, but mostly think about it as a means of information extraction

[freeone3000]

Putting the lookup in the AI means it can hallucinate the lookup. Putting the assesment of risk in the AI means it can fail on the assessment.

Please reconsider using a full text search index instead.

[DGrechko]

Good point. I’ll add it to the roadmap. I still want to experiment with AI features as I feel it can add value despite hallucinations, but safety and transparency are crucial - completely agree.