One way to assess the validity of prior claims is to see how many words you can ... | Hacker News

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

Kosturdistan 17 days ago | parent | context | favorite | on: AI Engineer Claims to Have Cracked Linear A

One way to assess the validity of prior claims is to see how many words you can translate using their proposed system.

qustio 17 days ago | [–]

But the entire corpus for Linear A is tiny, you could backfill a "translation" that has no actual similarity with the real language when properly tested against novel examples. How was this tested?

evilfred 17 days ago | [–]

of course we have no way to assess this claim as there is no public software or paper to review

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