AI agents: Less capability, more reliability, please

I don't really need an AI agent to book flights for me (I just don't travel enough for it to be any burden) but aren't those arguments for an AI agent? If you just wanna book the next flight London to New York it isn't that hard. A few minutes of clicking.

But if you wanna find the cheapest way to get to A, compare different retailers, check multiple peoples availability, calculate effects of credit cards etc. It takes time. Aren't those things that could be automated with an agent that can find the cheapest flights, propose dates for it, check availability etc with multiple people via a messing app, calculate which credit card to use, etc?

In theory, yes. But in a real world evaluation would it pick better flights? I'd like to see evidence that it's able to find a better flight that maximizes this. Also the tricky part is how do you communicate how much I personally weight a shorter flight vs points on my preferred carrier vs having to leave for the airport at 5am vs 8am? I'm sure my answers would differ from wiradikusuma's answers.

Yep that's what I've been thinking. This shouldn't be that hard, at this point LLMs should already have all the 'rules' (e.g. credit card A buys flight X give you m point which can be converted into n miles) in their params or can easily query the web to get it out. Dev need to encode the whole thing into a decision mechanism and once executed ask LLM to chase down the specific path (e.g. bombard ticket office with emails).

Yep this is my vibe.

When I'm picking out a flight I'm looking at, among other things:

* Is the itinerary aggravatingly early or late

* Is the layover aggravatingly short or long

* Is the layover in an airport that sucks

* Is the flight on a carrier that sucks

* What does it cost

If you asked me to encode ahead of time the relative value of each of these dimensions I'd never be able to do it. Heck, the relative value to me isn't even constant over time. But show me five options and I can easily select between them. A clear case where search is more convenient than some agent doing it for me.

I agree. At first I would be open to an LLM suggested option to appear in the search UI. I would have to pick it the majority of the time for quite awhile for me to trust it enough to blindly book through it.

It's the same problem with Alexa. I don't trust it to blindly reorder me basic stuff when I have to shift through so many bad product listing on the Amazon marketplace.

And what happens to the 1% where this fails? At the moment the responsibility is on the person. If I incorrectly book my flight for date X, and I receive the itinerary and realise I chose the wrong month - then damn, I made a mistake and will have to rectify.

An LLM could organise flights with a lower error rate, however, when it goes wrong what is the recourse? I imagine it's anger and a self-promise never to use AI for this again.

*If you're saying that the AI just supplies suggestions then maybe it's useful. Though wouldn't people still be double checking everything anyway? Not sure how much effort this actually saves?