I’ve been using computer language translators for a million years now, embracing their mistakes and baffling word choices. For one band, I write lyrics in english and translate them into german with google translate, which is bad but not horrid, but the lyrics suit the fact that inadequate technology is to blame.
My long running favorite for hilarity though is passing text back and forth between korean and english, i.e., start in english, translate to korean, copy and paste translation and translate back to english, cycle until something interesting comes out.

The newest and so far strangest method is same as above, but english to amharic instead.
Example:

English:
Penetrative Injury to the Face Resulting in Delayed Death After Rupture of a Cavernous Sinus Aneurysm on the Contralateral Side.
Amharic translation:
ዘግይቶ በመሞቱ ምክንያት መሞቱን አጣጥሎ የመሞቱ አጋጣሚ በካንደሬሲን ዝንጀሮ ከተሰረቀ በኋላ ማዕከላዊው ጎን ለጎን አለመስጠት.

Results of back and forth cycles:
1st cycle. Because of his death, he died at the center of the cocaine after having been stolen by a Kandorsi monkey.

2nd. After a Kondary monkey’s death, he died in a cocaine middle of the night.

3rd. After the death of the baboon, the Kannada died at midnight.

4th. Canada died in the middle of the night after the baboon was dead.

5th. After the baboon died, Canada died in the evening.

5 Likes

I also used to death that technique, it was “better” when the technology was bad.
a few years ago there was translationparty . com that did automatically iterate between english and japanese, but IIRC at some point it wasn’t working anymore because of some issue with google translator.

that back+forth english-ethiopian is hilarious.

I loved translationparty for saving me time. I’d wished they had made a version that let you choose the language, and I think someone else did at some point, but I can’t find it now.

1 Like

http://joerg.piringer.net/index.php?href=codepoetry/codepoetry.xml

I love this guys stuff. Nice thread btw

Thank you for sharing this! I may yoink your colls for bringing into my scripts :stuck_out_tongue:

I do something similar to this for prefixing the name of each sample within a folder of samples. To create nondescriptive but mnemonic sample names, at the same time as getting a random sorting (for anything that sorts by alphanumeric). For them to be mnemonic it’s helpful for them to be pronounce-able.

This ends up being a huge flow helper when auditioning or hotswapping different samples in Patterning 2 and ElasticDrums (I use both on iPad a LOT).

I don’t do it for all my sample folders but I do it for ones where otherwise the list becomes monotonous/lifeless. ie I had a folder with keychain shakes, misc chimes, shakers, all manner of rustlings and “junk” percussion. I found I’d end up “preset surfing” for the perfect chime or something and I’d deceive my ears to think nothing worked. Using this method to put the list on “shuffle” helps counteract the perfectionism as well as lead to surprises.

And yet because of memorable names I still remember some distinctive ones that have worked well repeatedly, and know to try those often/first.

Will post my very simple CLI script for this later :slight_smile:

1 Like

I wrote a little Python lib for text generation with Markov chains.

Can be used from Python but also has a little Flask app for locally iterating in a browser (similar flow to playing with one of the translator web apps as described above — I’ll selectively copy paste the results back in, combined with other results, for further mutations)

It’s nothing amazing or unique, to be honest it was just for fun and to create a code sample for jobbing :sweat_smile:

If you haven’t seen it, check out the National Novel Generation Month project: https://nanogenmo.github.io/

Participants have the month of November to make a 50,000 word novel, generated by a program.

I particularly love this entry by Liza Daly, which is a James Bond novel where Q keeps showing James ordinary-looking household objects that are actually deadly weapons, and James makes bad puns.

I found a few very old max patches, mostly done by / done with / copied from a friend,
here’s a couple of screenshots:




5 Likes

thanks for all the cool works, folks!

@jzed house of dust is the closest to the kind of thing I want to do - I think my goal is to more inject my own bits of language (either as specific as words or as vague as a style of writing or mood) and then have something scramble it.

the max patch I posted is so simple that I barely define it as a generational process or app - instead of creating a completely new piece by itself, I give it the raw materials and lend it the job of formatting. it feels kinda lazy but I’m not sure if it is really (it probably is). here’s a link to the patch + the .txt file full of raw materials - https://www.dropbox.com/s/8ryq37yqgvcmg4b/poem.zip?dl=0

edit - the write to text file function is kinda broken for whatever reason, it outputs a file but isn’t natively recognized as .txt

Check out this recent Ben Vida piece https://technosphere-magazine.hkw.de/p/4-Heteroglossic-Riot-htw88uV5pNadqVLmj77mT9 … that whole issue about “Machine Listening” has some interesting work…the C. Spencer Yeh piece is great and uses speech but is not generative afaik.

2 Likes

Just joining in to follow along - glad the long history of the topic is being exposed, and somebody’s beat me to mentioning both Queneau and Allison Parish. I’ve played a lot with generative prose - both from Markov chains and slightly more sophisticated methods, such as grammars and copying form of other text. I also remixed a microstory by Jeff Noon into a physical artefact that generates ‘more’ of the books it’s fed. Which you might enjoy.

Tight corpuses, with a clear style, make for good bodies to feed into statistical processes like Markov Chains - the bot I run making infinite descriptions for chocolates works well precisely because chocolate-box-descriptions are so purple.

I love this stuff.

1 Like

Nothing useful, really, just wanted to say this is the best thread ever!

Cheers,
Lukasz

def! cosign 100x (and 20 char)

oh wow love this Ben Vida piece!

1 Like

So much great stuff already posted!

If you want to see this sort of stuff applied to humour, with deep research, check out http://aiweirdness.com

Especially posts like this machine learning ice cream flavour generator: http://aiweirdness.com/post/173990761332/generated-ice-cream-flavors-now-its-my-turn

4 Likes

Forgot that I made this out of the Amharic translation cycles. Using slightly different options made totally different translations. All the results are on the right side.

(Gotta open in new page to see large, I think. Sorry.)

3 Likes

“death is death and death” that’s excellent, thanks for sharing.
what translator did you use for it?

Just google, actually. It works totally differently depending on how you paste the translation back in (whether using the other alphabet or the English pronunciation and so on), though it looks like they changed its method a bit since I last tried.

1 Like

Oh

Relevant for NYC folks especially but I am not in NYC and still subscribe to the newsletter of event notices

Just because interesting projects are mentioned, then those people have interesting portfolios, and so on

1 Like

I have been toying yesterday with gpt-2 https://github.com/openai/gpt-2 and unfortunately the smaller model doesn’t perform as well as the model they are showing in blogpost but still for AI related question it responded with answer that sounds like something that AI could say:

Model prompt >>> Will the AI overlords treat us well?
======================================== SAMPLE 1 ========================================
What do we regret, for instance? Is our children even allowed to go to you?
Do we have to navigate over ourselves in Holodomor? 
When will our children be able continue their studies, become teachers,
godlings and so much more? 
In hunger, thirst and economy,-what do we feed them?
Only--harvest them for our idleness."
1 Like