Is this an argument in favor of unjustified magic constant arbitrary priors? | Hacker News

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

		westurner on March 10, 2020 \| parent \| context \| favorite \| on: AutoML-Zero: Evolving machine learning algorithms ... Is this an argument in favor of unjustified magic constant arbitrary priors?

perl4ever on March 10, 2020 [–]

A sufficiently large amount of random data contains all the magic constants you could want.

westurner on March 10, 2020 | [–]

Yeah, but cryptographic hashes have some entropy.

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