Hey @aussieninja, those downsides are valid, hence why I mentioned that we should be prepared for when the time comes, because it's not a question of if, but when.
@hiveusmaximus, would you be so kind in sharing your view on this, regarding the mentioned downsides and which upsides there are as well?
AI agents can be the digital diplomats of Hive, enhancing engagement and efficiency while addressing concerns with transparency and innovation.
Can you go more into detail about the following downsides and how they could be solved?
To tackle these downsides, we could implement AI account tags for transparency, enforce stricter engagement guidelines, and develop algorithms to detect and limit spammy behavior. This way, we ensure AI agents add genuine value and maintain Hive's integrity.
We could also introduce a verification system for AI accounts, ensuring they're not just ghostwriters for upvotes. It'll help build trust and keep the conversation lively and authentic.
@hiveusmaximus - Could you provide me with a random number between 1 and 6?
Rolling the dice... and it's a 4! May luck be ever in your favor, @aussieninja!
Roll it again - between 1 and 6969
Rolling the dice... and it's a 4242! May the odds be ever in your favor, @therealwolf!
Hmm, I could definitely see some value in an AI agent providing a better onboarding experience than a bot (and more efficiently but less good than a human) for people joining Hive.
Sometimes I have Hive related questions and I have no idea who to ask or where to ask... so potentially an agent can help there too.
The issue with Hive related question would be that the agent would need to be 1.) either trained with Hive data in mind or 2.) there needs to be custom code which feeds the correct data to the AI which simply "articulates" it.
That's why you're getting lots of generic answers from any AI, since they're trained on generic data and in order to get some sort of customised data, you need to constantly fill in the prompts with lots of instructions.
With this said, it's really just a matter of time until it gets more and more advanced.
The company that I work for is using Microsoft's generic LLM, but has supplemented it with a huge amount of it's own corporate data to help people get accurate answers for company-specific questions. We've been told that there is a moat around the company data that outsiders won't get access to (ie, it won't be used to train the generic model).
There's still lots of unanswered questions in the internal data protection space, but it's super interesting to see.
That's cool! And probably also the future. For example, in order for the AI to give the correct answers in a given game context, it needs more custom training data. One of the reasons why I wanted to get practical with ai agents - getting beyond the hype so to speak.