←back to thread

AI agents: Less capability, more reliability, please

(www.sergey.fyi)
419 points serjester | 1 comments | 31 Mar 25 14:45 UTC | HN request time: 0.342s | source
Show context
simonw ◴[31 Mar 25 15:08 UTC] No.43535919[source]▶
Yeah, the "book a flight" agent thing is a running joke now - it was a punchline in the Swyx keynote for the recent AI Engineer event in NYC: https://www.latent.space/p/agent

I think this piece is underestimating the difficulty involved here though. If only it was as easy as "just pick a single task and make the agent really good at that"!

The problem is that if your UI involves human beings typing or talking to you in a human language, there is an unbounded set of ways things could go wrong. You can't test against every possible variant of what they might say. Humans are bad at clearly expressing things, but even worse is the challenge of ensuring they have a concrete, accurate mental model of what the software can and cannot do.

replies(12): >>43536068 #>>43536088 #>>43536142 #>>43536257 #>>43536583 #>>43536731 #>>43537089 #>>43537591 #>>43539058 #>>43539104 #>>43539116 #>>43540011 #
yujzgzc ◴[31 Mar 25 16:50 UTC] No.43537089[source]▶
I'm old enough to remember having to talk to a (human) agent in order to book flights, and can confirm that in my experience, the modern flight booking website is an order of magnitude better UX than talking to someone about your travel plans.
replies(3): >>43537397 #>>43539127 #>>43542842 #
1. kccqzy ◴[31 Mar 25 17:19 UTC] No.43537397[source]▶
That still exists. The last time I did onsite interviews, every single company that wanted to fly me to their office to interview me asked me to talk to a human agent to book flights. But of course the human agent is just a travel agent with no budgetary power; so I ended up calling the agent to inquire about a booking, then calling the recruiter to confirm that price is acceptable, and then calling the agent book to confirm the booking.

It doesn't have to be this way. Even before the pandemic I remember some companies simply gave me access to an internal app to choose flights where the only flights shown are these of the right date, right airport, and right price.