Hacker News Reader

Comment by bagels | Hacker News Reader

Doesn't even make sense. Babies cry all the time for a multitude of reasons, none of which are informed by how many diapers are in the house.

View on HN

Babies just need to learn to cry only when the diapers in the garage are running low. How hard could that be?

Clearly the feedback loop is too long currently. If we could instantly dispense diapers onto the baby as soon as it started crying, that would improve learning outcomes and encourage experimentation.

Sounds like a virtuous cycle to me!

Babies who cry a little at a time will be awash with diapers, leading to secondary market opportunities. Now we just need a two-sided marketplace to capture that business and charge a modest fee.

Interestingly, there is an app, Chatterbaby [1], that claims to detect why a baby is crying based on the acoustic features of the cry. I've used it with middling success.

That'd be a neat integration: "Alexa, why is my baby crying?"

[1]: https://www.chatterbaby.org/pages/

https://www.nature.com/articles/s41390-019-0592-4

"Your baby is crying because it doesn't like the brand of formula you purchase. We recommend Amazon Basics!"

"We recommend you try UBQTLONR this time!"

Now with extra melamine!

"Your baby is crying because you often raise your voice and make unreasonable demands of those around you. Would you like to add insurance for a lifetime of psychiatric help to your cart?"

This sounds like a joke but Amazon made a device specifically to listen to people talk all day and tell them how they sound to others. It is called Halo.

Your baby is crying over the intrusion of big tech into their private life before they even have object permanence.

Yeah and given how often we get it wrong as parents, imagine the absolute dumpster fire it would be to have a voice assistant get it 10x as wrong.

Reply on news.ycombinator.com