Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> they don't have any common sense

What do you mean by this? Of course they do, learned from their training data. For example, here is quote from conversation 38 of https://github.com/google-research/google-research/blob/mast...

Human: Do you like Korean food in general? Meena: It's okay. I like beef bulgogi, but I'm not a huge fan of kimchi.

It seems to me Meena "knows" bulgogi and kimchi are Korean foods. Isn't that common sense? If it isn't, what do you mean by "common sense"?



Try asking it a follow up question not commonly found in the training data: such as "do you think bulgogi would grow on Mars?", and see what kind of gibberish you will get in response. Moreover, the model has no way of self-diagnosing whenever it produces gibberish.


What is the baseline comparison here? If you asked a random 100 people on the street this question?


I'd buy that if Meena could infer and reason about her own answers.

Human: Do you like Korean food in general?

Meena: It's okay. I like beef bulgogi, but I'm not a huge fan of kimchi.

Human: Ok what should I shop for ?

Meena : You've got almost everything but you need a pear, the steak and some ginger.

The problem with language models as commonsense is that they are collections of patterns and associations, and that they don't have inference models or solvers - unlike my dog for example!


unlike my dog for example!

A more relevant analogy might be a talking parrot :)


Parrots might have what we call a language model... They definitely have inference and autonomy!




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: