News for hackers. Stuff that matters.

A comment on Why are we using black box models in AI when we don’t need to? (2019). Parent comment

Re:Why are we using black box models in AI when we don’t nee... by tdhttt on Sunday January 05, 2020 @04:31AM (#21960488)
One more benefit: an interpretable model could at least give some hint when the model is not working as intended (e.g. debugging).
[ Parent | on HN ]
Re:Why are we using black box models in AI when we don’t nee... by choeger on Sunday January 05, 2020 @06:12AM (#21960738)
Sometimes I have the feeling that this is exactly why so many people prefer black-box modeling. You are not going to be criticised and you don't have to do all the hard work of software development.
[ Parent | on HN ]