This is a very fun idea, and seems very useful. But just from a glance it doesn't seem the most user friendly.
I think it would also be helpful to have something of a guide for the first (few) case(s). I could have missed it if you have one, but the AI hit me like a truck. Turns out it is more difficult to BS an AI that is only designed to do one thing than a regular LLM...
I like the concept, and I think that as long as there is an explanation of what works and why, it could be an interesting learning tool.
I like this but after 3-4 messages I got the AI to agree that my flight should be refunded yet the confidence was not zero. The tips just said to keep explaining why the particular law applies in my situation but I already kinda did that.
This is a very fun idea, and seems very useful. But just from a glance it doesn't seem the most user friendly.
I think it would also be helpful to have something of a guide for the first (few) case(s). I could have missed it if you have one, but the AI hit me like a truck. Turns out it is more difficult to BS an AI that is only designed to do one thing than a regular LLM...
I like the concept, and I think that as long as there is an explanation of what works and why, it could be an interesting learning tool.
I like this but after 3-4 messages I got the AI to agree that my flight should be refunded yet the confidence was not zero. The tips just said to keep explaining why the particular law applies in my situation but I already kinda did that.
I really love this, it's a smart and practical idea to turn the frustrating failures of AI in the real world into a learning game.