Any AI will be flawed, it is human created and fed human content.
Bad content in = bad content out.
Using the internet as a source will only provide generic information with specifics and context being incorrect.
The hardest part of building an agent is sanitising the data sources.
We are also likely to see models retrained on content that contains increasing amounts of already-generated content, so that is the snake eating its own tail.
In Victron’s case you could train your own model, though this is really expensive, or pick one that works and feed it a Victron specific diet of supplementary data that is known to be good.
Feeding it all the (previous) forum topics did not yield good results.
Even then, it will help find better data in a broader context, but, since any AI lacks intuition, when it comes to scenario specific answers and differentiating between relevant scenarios, it still will not be a substitute for an experienced and, ironically, trained, professional.
These aren’t one size fits all systems.
I think we would all be happy if it can bridge the gap for the majority of FAQ’s which represent most of the queries, on this forum at least.
I think for this point finding information with AI. Sure.
But we don’t want answers cooked up by AI here.
Too many people will just regurgitate (without enough chewing) what AI tells them, post here, then mods will be in a living nightmare.
It is the heavily structured nature of a topic that will get things flagged, the topic just does not read like a natural person writing to a human community, it reads like something parsed by an LLM. It is not about AI generation alone, it applies to numerous and increasing amounts of content that has used LLM assistance to structure or format a post.
We have a fairly smart current LLM with specific criteria that assesses if the content meets multiple hallmarks of AI assistance, and yours hits several, hence the flag. It does get it wrong from time to time, in which case they are released, a bit like the spam filter.
