Applying information theory out of its domain is nonsensical, yes. That's the po... | Hacker News

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

littlestymaar 9 months ago | parent | context | favorite | on: Self-supervised learning, JEPA, world models, and ...

Applying information theory out of its domain is nonsensical, yes. That's the point.

And for that reason, your argument about 1GB of data makes absolutely no sense at all.

ACCount37 9 months ago [–]

Bullshit. We're talking about information, and were always talking about information.

littlestymaar 9 months ago | [–]

The problem is that you claim that you can quantify it based on bad use of irrelevant tools.

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