Google develops AI tool that fills missing words in Roman inscriptions

Comments

• Lumidaub@feddit.org ⁨3⁩ ⁨weeks⁩ ago

  I bet I could do that too, hallucinate some bullshit that seems like it could fit in the gaps.

  source

  • SkybreakerEngineer@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

    Romanes eunt domus

    source
  • friend_of_satan@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

    Seriously. lemmy.world/post/33375695

    source
• dhork@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

  Who knew this inscription wad about “Biggus Dickus” all along?

  source

  • jubilationtcornpone@sh.itjust.works ⁨3⁩ ⁨weeks⁩ ago

    Does it also mention his wife, Incontonentia Buttocks?

    source

    • ThePyroPython@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

      What about Naughtimus Maximus?

      source
• prex@aussie.zone ⁨3⁩ ⁨weeks⁩ ago

  Who knew the Romans were such big fans of squarespace?

  source
• nyan@lemmy.cafe ⁨3⁩ ⁨weeks⁩ ago

  It isn’t quite as crazy as it sounds when you consider that a lot of inscription texts are pretty formulaic—epitaphs, dedications, and such. Plus, we have plenty of surviving writings in classical Latin, so we know the grammar pretty well. Given those things, I’d expect an AI trained on the corpus of inscription texts that have survived without significant damage to be able to make reasonable suggestions about formulaic texts.

  Really, when you think about it, a trained human presented with a damaged inscription text won’t be doing anything much different from what an LLM would do: they’ll try to fill in the text with the most likely words based on any remaining traces of letters, and their knowledge of other, similar texts. The problem is getting the LLM to communicate its level of certainty about the fill-ins it’s offering.

  source

  • FishFace@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

    That and (at least for now) it may be difficult to communicate contextual information to an LLM that a human historian or philologist may be able to take in implicitly.

    source
• qwestjest78@lemmy.ca ⁨3⁩ ⁨weeks⁩ ago

  What a joke

  source
• isodimensional@aussie.zone ⁨3⁩ ⁨weeks⁩ ago

  This has actually been done for quite a long time. Roman historians could look up common words in databases from partial words and get a pretty good guess at the overall inscription from context.

  source
• db2@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

  Neque porro quisquam est qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit.

  source