AI in conlanging - present and future
Re: AI in conlanging - present and future
such a quantity of words is irrelevant,
even if generative artificial "intelligences"
try to replace the qualitative by the quantitative,
but all they produce is barroom talk with an erudite dummy...
even if generative artificial "intelligences"
try to replace the qualitative by the quantitative,
but all they produce is barroom talk with an erudite dummy...
Re: AI in conlanging - present and future
given that this is AI, does - for it - count code and-or HTML as words?zompist wrote: ↑Sat May 11, 2024 5:16 amThere are some estimates of the total size of the Internet, but I don't think they're comparable... consider how much of the Internet is pictures, video, HTML codes, or other code.I got ChatGPT to estimate the total number of words it has been exposed to in all of its training. [...]
It’s ultimate estimate, IIRC, was 5 quintillion.
-
- Site Admin
- Posts: 2912
- Joined: Sun Jul 08, 2018 5:46 am
- Location: Right here, probably
- Contact:
Re: AI in conlanging - present and future
Doing some Googling, it appears GPT-4 was trained on 13 trillion tokens. (Tokens are somewhere between words and morphemes.) At that level of analysis, I don't think they're separating out programs from human language.keenir wrote: ↑Sat May 11, 2024 11:55 pmgiven that this is AI, does - for it - count code and-or HTML as words?zompist wrote: ↑Sat May 11, 2024 5:16 amThere are some estimates of the total size of the Internet, but I don't think they're comparable... consider how much of the Internet is pictures, video, HTML codes, or other code.I got ChatGPT to estimate the total number of words it has been exposed to in all of its training. [...]
It’s ultimate estimate, IIRC, was 5 quintillion.
That's nowhere near 5 quintillion, so I think ChatGPT got confused here.
Re: AI in conlanging - present and future
You’re quite right. I assumed the figure came from training corpus plus input from other AIs plus interactions with users, but didn’t interrogate that particularly well.
Here’s ChatGPT’s explanation:
I didn’t save the chat where the very large estimate was given, so I can’t remember how it got there.
Here’s ChatGPT’s explanation:
More: show
I didn’t save the chat where the very large estimate was given, so I can’t remember how it got there.
Re: AI in conlanging - present and future
as my ai-enabled search engine says,
“AI-generated response. Remember to check important information”...
believe me, but not too much...
“AI-generated response. Remember to check important information”...
believe me, but not too much...
-
- Posts: 525
- Joined: Tue Mar 16, 2021 4:09 pm
- Location: Poland
Re: AI in conlanging - present and future
AI models are getting better at conlanging. The following text is a courtesy of Claude 3.5 Sonnet. Which language is this conlang descended from?
On heste tid, sceap tat hæfde næn ull sæh hesta on feld. An drog swær wagn, oter bær micele byrten, and tridde bær mann swiftlice.
Sceap cwæt to hestum: "Min heorte is sær, tonne ic seo mann ridan hesta."
Hestas cwædon: "Hlyste, sceap! Ure heortan sint sære tonne we seot: mann, hlaford, macet ull of sceapum to warm clatum for him sylf. And sceap hæft næn ull."
Ta sceap hærde tis, hit fleah into feld.
IPA transcript:
/ɔn heste tiːd ʃeːap tat hæfde næːn ul sæːh hesta ɔn feld an drɔg swæːr wagn ɔter bæːr mikele byrten and tride bæːr man swiftlike/
/ʃeːap kwæːt tɔ hestum miːn heorte is sæːr tɔne ik seːo man riːdan hesta/
/hestas kwæːdɔn hlyste ʃeːap uːre heortan sint sæːre tɔne weː seːot man hlaːfɔrd maket ul ɔf ʃeːapum tɔ warm klaːtum fɔr him sylf and ʃeːap hæːft næːn ul/
/ta ʃeːap hæːrde tis hit fleːah intɔ feld/
On heste tid, sceap tat hæfde næn ull sæh hesta on feld. An drog swær wagn, oter bær micele byrten, and tridde bær mann swiftlice.
Sceap cwæt to hestum: "Min heorte is sær, tonne ic seo mann ridan hesta."
Hestas cwædon: "Hlyste, sceap! Ure heortan sint sære tonne we seot: mann, hlaford, macet ull of sceapum to warm clatum for him sylf. And sceap hæft næn ull."
Ta sceap hærde tis, hit fleah into feld.
IPA transcript:
/ɔn heste tiːd ʃeːap tat hæfde næːn ul sæːh hesta ɔn feld an drɔg swæːr wagn ɔter bæːr mikele byrten and tride bæːr man swiftlike/
/ʃeːap kwæːt tɔ hestum miːn heorte is sæːr tɔne ik seːo man riːdan hesta/
/hestas kwæːdɔn hlyste ʃeːap uːre heortan sint sæːre tɔne weː seːot man hlaːfɔrd maket ul ɔf ʃeːapum tɔ warm klaːtum fɔr him sylf and ʃeːap hæːft næːn ul/
/ta ʃeːap hæːrde tis hit fleːah intɔ feld/
- WeepingElf
- Posts: 1482
- Joined: Sun Jul 15, 2018 12:39 pm
- Location: Braunschweig, Germany
- Contact:
Re: AI in conlanging - present and future
Old English.Otto Kretschmer wrote: ↑Mon Jun 24, 2024 9:12 am AI models are getting better at conlanging. The following text is a courtesy of Claude 3.5 Sonnet. Which language is this conlang descended from?
On heste tid, sceap tat hæfde næn ull sæh hesta on feld. An drog swær wagn, oter bær micele byrten, and tridde bær mann swiftlice.
Sceap cwæt to hestum: "Min heorte is sær, tonne ic seo mann ridan hesta."
Hestas cwædon: "Hlyste, sceap! Ure heortan sint sære tonne we seot: mann, hlaford, macet ull of sceapum to warm clatum for him sylf. And sceap hæft næn ull."
Ta sceap hærde tis, hit fleah into feld.
IPA transcript:
/ɔn heste tiːd ʃeːap tat hæfde næːn ul sæːh hesta ɔn feld an drɔg swæːr wagn ɔter bæːr mikele byrten and tride bæːr man swiftlike/
/ʃeːap kwæːt tɔ hestum miːn heorte is sæːr tɔne ik seːo man riːdan hesta/
/hestas kwæːdɔn hlyste ʃeːap uːre heortan sint sæːre tɔne weː seːot man hlaːfɔrd maket ul ɔf ʃeːapum tɔ warm klaːtum fɔr him sylf and ʃeːap hæːft næːn ul/
/ta ʃeːap hæːrde tis hit fleːah intɔ feld/
... brought to you by the Weeping Elf
My conlang pages
My conlang pages
Re: AI in conlanging - present and future
To clarify, is it outright OE text, and not descended from it?
/j/ <j>
Ɂaləɂahina asəkipaɂə ileku omkiroro salka.
Loɂ ɂerleku asəɂulŋusikraɂə seləɂahina əɂətlahɂun əiŋɂiɂŋa.
Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ.
Ɂaləɂahina asəkipaɂə ileku omkiroro salka.
Loɂ ɂerleku asəɂulŋusikraɂə seləɂahina əɂətlahɂun əiŋɂiɂŋa.
Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ. Hərlaɂ.
- WeepingElf
- Posts: 1482
- Joined: Sun Jul 15, 2018 12:39 pm
- Location: Braunschweig, Germany
- Contact:
Re: AI in conlanging - present and future
I am not an expert on Old English, but to me it looks just like outright Old English, not a conlang descended from it.
... brought to you by the Weeping Elf
My conlang pages
My conlang pages
Re: AI in conlanging - present and future
I'd agree with this, or perhaps suggest that it looks like a particularly good sample of Markov-generated text from OE inputs.WeepingElf wrote: ↑Mon Jun 24, 2024 1:15 pmI am not an expert on Old English, but to me it looks just like outright Old English, not a conlang descended from it.
Self-referential signatures are for people too boring to come up with more interesting alternatives.
- WeepingElf
- Posts: 1482
- Joined: Sun Jul 15, 2018 12:39 pm
- Location: Braunschweig, Germany
- Contact:
Re: AI in conlanging - present and future
It is obviously Schleicher's Fable, in a Germanic language that looks like Old English - but it doesn't really seem to be that, rather it seems to show some North Germanic traits, such as hest 'horse' or ull 'wool'. My guess is that it is a bogolang, obtained by running Old Norse through the sound changes from Common (West) Germanic to Old English. This kind of thing doesn't really require AI, just a sound change applieralice wrote: ↑Mon Jun 24, 2024 3:04 pmI'd agree with this, or perhaps suggest that it looks like a particularly good sample of Markov-generated text from OE inputs.WeepingElf wrote: ↑Mon Jun 24, 2024 1:15 pmI am not an expert on Old English, but to me it looks just like outright Old English, not a conlang descended from it.
... brought to you by the Weeping Elf
My conlang pages
My conlang pages