←back to thread

419 points serjester | 1 comments | | HN request time: 0.341s | source
Show context
jedberg ◴[] No.43538462[source]
I've been working on this problem for a while. There are whole companies that do this. They all work by having a human review a sample of the results and score them (with various uses of magic to make that more efficient). And then suggest changes to make it more accurate in the future.

The best companies can get up to 90% accuracy. Most are closer to 80%.

But it's important to remember, we're expecting perfection here. But think about this: Have you ever asked someone to book a flight for you? How did it go?

At least in my experience, there's usually a few back and forth emails, and then something is always not quite right or as good as if you did it yourself, but you're ok with that because it saved you time. The one thing that makes it better is if the same person does it for you a couple of times and learned your specific habits and what you care about.

I think the biggest problem in AI accuracy is expecting the AI to be better than a human.

replies(2): >>43538574 #>>43538649 #
1. morsecodist ◴[] No.43538574[source]
This is really cool. I agree with your point that a human would also struggle to book a flight for someone but what I take from that is conversation is not the best interface for picking flights. I am not really sure how you beat a list of available flights + filters. There are a lot of criteria: total fight time, price, number of stops, length of layover, airline, which airport if your destination is served by multiple airports. I couldn't really communicate to anyone how I weigh those and it shifts over time.