> Chatting through all the races and the different candidates, he worked to figure out who best represented his values.

This sounds like it can be a really good thing. In an ideal world it’s a perfect use of LLMs. It helps make the ballot more approachable to people, and it can encourage more people to vote or help people vote less blindly.

At the same time, it also relies on these tools being unbiased adjudicators. And over time I think there’s a greater risk of this straying from the truth.