WrenP-Complete posted:

https://twitter.com/eripsabot/status/851228060347183105

https://twitter.com/eripsabot/status/851223901376053248

Silver Alicorn posted:

for your hell

quote:

The Silicon Gourmet: training a neural network to generate cooking recipes
Neural networks are computer learning algorithms that mimic the interconnected neurons of a living brain, managing astonishing feats of image classification, speech recognition, or music generation by forming connections between simulated neurons.

I’m not a neural network researcher, but there’s never been a better time to experiment with them, thanks to open-source packages like torch, a scientific computing framework with built-in neural network capabilities. Inspired by Tom Brewe’s neural network-generated recipes, and enabled by the open-source torch add-on for character-based neural networks by Andrej Karpathy, I fired up the neural network code on my 2010 Macbook Pro, and started training it on a bunch of recipes I downloaded from a collection by David Shields.

Here’s a recipe my network has generated:

Pears Or To Garnestmeam

meats

¼ lb bones or fresh bread; optional
½ cup flour
1 teaspoon vinegar
¼ teaspoon lime juice
2 eggs

Brown salmon in oil. Add creamed meat and another deep mixture.

Discard filets. Discard head and turn into a nonstick spice. Pour 4 eggs onto clean a thin fat to sink halves.

Brush each with roast and refrigerate. Lay tart in deep baking dish in chipec sweet body; cut oof with crosswise and onions. Remove peas and place in a 4-dgg serving. Cover lightly with plastic wrap. Chill in refrigerator until casseroles are tender and ridges done. Serve immediately in sugar may be added 2 handles overginger or with boiling water until very cracker pudding is hot.

Yield: 4 servings
This is from a network that’s been trained for a relatively long time - starting from a complete unawareness of whether it’s looking at prose or code, English or Spanish, etc, it’s already got a lot of the vocabulary and structure worked out.

This is particularly impressive given that it has the memory of a goldfish - it can only analyze 65 characters at a time, so by the time it begins the instructions, the recipe title has already passed out of its memory, and it has to guess what it’s making. It knows, though, to start by browning meat, to cover with plastic wrap before chilling in the refrigerator, and to finish by serving the dish.

Compare that to a recipe generated by a much earlier version of the network:

Immediately Cares, Heavy Mim

upe, chips

3 dill loasted substetcant
1 cubed chopped whipped cream
3 unpreased, stock; prepared; in season
1 oil
3 cup milk
1 ½ cup mOyzanel chopped
½ teaspoon lemon juice
1 ¼ teaspoon chili powder
2 tablespoon dijon stem – minced
30 dates afrester beater remaining

Bake until juice. Brush from the potato sauce: Lightly butter into the viscin. Cook combine water. Source: 0 25 seconds; transfer a madiun in orenge cinnamon with electres if the based, make drained off tala whili; or chicken to well. Sprinkle over skin greased with a boiling bowl. Toast the bread spritkries.

Yield: 6 servings
which bakes first, has the source in the middle of the recipe directions, mixes sweet and savory, and doesn’t yet know that you can’t cube or chop whipped cream.

An even earlier version of the network hasn’t yet figured out how long an ingredients list should be; it just generates ingredients for pages and pages:

Tued Bick Car

apies

2 1/5 cup tomato whene intte
1 cup with (17 g cas pans or
½ cup simmer powder in patsorwe ½ tablespoon chansed in
1 ½ cup nunabes baste flour fite (115 leclic
2 tablespown bread to
¼ cup 12". oz mice
1 egg barte, chopped shrild end
2 cup olasto hote
¼ cup fite saucepon; peppen; cut defold
12 cup mestsentoly speeded boilly,, ( Hone
1 Live breseed
1 22 ozcugarlic
1 cup from woth a soup
4 teaspoon vinegar
2 9/2 tablespoon pepper garlic
2 tablespoon deatt
…
And here’s where it started out after only a few tens of iterations:

ooi eb d1ec Nahelrs egv eael
ns hi es itmyer
aceneyom aelse aatrol a
ho i nr do base
e2
o cm raipre l1o/r Sp degeedB
twis e ee s vh nean ios iwr vp e
sase
pt e
i2h8
ePst e na drea d epaesop
ee4seea .n anlp
o s1c1p , e tlsd
4upeehe
lwcc eeta p ri bgl as eumilrt
Even this shows some progress compared to the random ASCII characters it started with - it’s already figured out that lower case letters predominate, and that there are lots of line breaks. Pretty impressive!

Crusader posted:

what in the gently caress, why isn't godzilla winning here

https://twitter.com/WYR_bot/status/863876961785040897

Powaqoatse posted:

its creepy as gently caress to post pictures of your sister on the internet

Eripsa posted:

Hello YOSPOS! I have an idea for a crowdsourced Turing test web tool for evaluating the conversational abilities of Twitter bots. WrenP has pointed me to Botometer which uses traditional bot detection with sentiment analysis to guess if an account is a bot. But I was thinking of something more traditionally akin to Turing's test.

The tool I imagine does two things: first, it lets you submit links to specific tweets. The tool grabs that tweet and the reply chain, including any replies to and from the original tweeter.

Second, the tool shows you sample exchanges from its database, formatted like twitter but scraped of identifying information, and asks the reader to judge: Bot or not? Perhaps then the reader is told the correct answer, if known.

The tool then scores bots on how often they are confused for human speakers. Ideally, the results would be interesting enough to rate twitter bots on their skills as interlocutor, perhaps to be worn as a badge of honor. Perhaps we could have other bots assigning ratings also, and maintain a score for how well a bot convincing humans, and a separate score for convincing other bots.

Developing this tool doesn't seem to me hard to do from a technical perspective, but I tend to underestimate such things. I would be happy to supply/acquire reasonable funding for such a project; I have webspace and I just squatted on turingtest.chat for a place to put it.

Any thoughts?

Synthbuttrange posted:

someone taught a bot to do the unthinkable.

Generate anime avatars.

http://mattya.github.io/chainer-DCGAN/

Enola Gay-For-Pay posted:

Agile Vector posted:

WrenP-Complete posted:

The immediacy of the ball "this ball" contrasted with the distance of "a horrible horse" is the sticking point for me.

carry on then posted:

Obama chuckled. "You mean the Chaos Senators?"

Rollersnake posted:

original character do not steal

Also, where the gently caress is it getting Ginsburg from?

quote:

There were also some like this:

Rink Rater Ginsburg
A winged boxer Ginsburg
Bed ridingh in a box Buther Ginsburg
Skeleton Ginsburg
Zombie Fire Cith Bader Ginsburg
Because someone had entered about 50 variations on Ruth Bader Ginsberg puns (Ruth Tater Ginsberg, Sleuth Bader Ginsber, Rock Paper Ginsberg).

Captain Foo posted:

5

NoneMoreNegative posted:

Attn: Trig

http://aiweirdness.com/post/167343465812/the-neural-network-meets-its-match-fish

code:

Black Sea sweetlips
Eastern Dear eel
Oastern nose sucker
Vermillion assfin
Cuban fork head sucker
Gempofloise sand flaky
Vumberfish
Gerpike dwarf monocle bream
Wrink clown-shark
Bluebanded smooth-eet
Bluebacked tube-spot skate
Wallare pipe-eyed parrotfish
Moon-lined wad
Kascopcan tonguefish
Highfin stonebasher

Dantuman ghost puffer
Moo lanternfish
Darfer butterflyfish
Hornmack croaker
Horny deepwater darter
Horseshark
Orangespotted smooth-hound
Yellow-black yellowtail dragonet
Small-dotted catshark
Small-mouthed unicorn fish
Orangespotted tilefish
Horse-eye grunt
Horse-snout fang-tailed dogfish
Pacific squeaker
Pacific headless lamprey
Little weakfish

Mottonsfish
Danubiec spring-striped lumpsucker
Kaire-fin eartheater
Sputtail
Vague-lined sleeper-banded soapfish
Dangle shark
Dauis deepwater redhorse
Khans hound shark
Rathead batfish
Lanto sand tiger unicorn fish
Bockon cubehead
Bow spiny lumpsucker
Boster weedfish
Deep dogfish
Binders flathead parrotfish
Hawaiian Stump ray
Black Sea gardenfish
Black Sea jobfish
Horny humbug

Short-nose batfish
Short-nosed leatherjacket
Short-nosed jewelled-eyed rainbowfish
Short-lined pigfish
Short-toothed trumpeter
Short-face shrampgoby
Short-headed hogfish
Bokinkers tubeshoulder
Bottlenose wobbegong
Bostriebann flute-tooth wolffish
Boguu dragonet
Pighead mullet

Moanygoby
Mottled utterfish
Kacks coral gropes
Kalhal gardensean block ray
Wurp fish
Whitley assfish
Sudderspot happy ghost-perch
Sucking puller
Sunsetnose spider shark
Witcheefin squirrelfish
Orangeside slickhead
Hawaiian doctorfish
Chornacher comb-tooth
Black Sea lampeye
Striped flying fang loach
Striped hone-spine dottyback
Greater butterfly tube-snouted ghost knifefish
Cuban armoured cat

I am of course a Horse-snout fang-tailed dogfish

atomicthumbs posted:

death before dishonor