Zeke Fiddler


Dabbler, Doodler, Generalist,

3,578 words

Thank Guestbook
You'll only receive email when Zeke Fiddler publishes a new post

My Haunted Text Editor

You want to know how to easily annoy my wife?

I'm sure that she can tell you a million ways to Sunday how I've already managed to pull this off at least a thousand times since sunrise.... But that is my own special talent, and not one which I readily share with others.

As far any random friend or stranger is concerned however, they for sure could usher her into the express lane to Grumpy Town by simply offering to recap their previous night's dream.

Really though, who could blame her? I mean, you have to admit, that sort of garbage is pretty freakin annoying. Frankly, if you are an adult and are still in the least bit surprised by the quality of crap your subconscious chooses to belch on any given night, not to mention, entertaining the thought that it might rise to the level of being even remotely interesting enough to share outloud.... well then...let me take this opportunity to tell you about my dreams from last night too.... so please, feel free to kick back while I attempt to recount to you in exacting detail......

There I was, minding my own beezwax while we were all crammed into this tiny car, headed out on the highway, making our way to the Big Rock Candy Mountain...., You were reading the new Phone Book to us

Aaron, Abal........12 Hunkner Downs Circle .... (413) 555-8080
Aaron, Abraham.....701 Nowhere Place .......... (413) 555-5809
Aaron, Acer........111 You Get My Drift Ct .... (413) 55555555555555

And you were in the driver's seat.... Only you weren't driving...because......well...you had the phonebook in your hands... Isn't that Weird?.... And this talking goat was riding shotgun... only it wasn't a goat, but rather a chinchilla with a goatee.....Oh wait....Not a chinchilla, but a marmot...and I think it was singing the chorus to I Will Follow...only the words were different..."I feel hollow!!"...at least I think that was what it was singing...I recall that it might have had a very thick chinchillean accent...not so sure now.... anyway the important thing is... or at least seemed to be at the time ... that it was wearing a Pavement T-Shirt, but it had a picture of Jennifer Herrema from the Royal Trux on it....which made it a valuable collector's item... and a kid from the nearby college radio station was trying to take it from me..chinchilla and all...I tired to run, but I found that I could barely lift my feet.... and that's when all my teeth fell out. Just then, Ash from Polvo showed up with a 16mm print of Shakes the Clown in hand... He asked if anyone had a moviola, and we scattered to the far corners of the earth trying to dig one up..... Did I mention the stuff about Nick Cave, Debbie Harry riding dinosaurs yet?

Aaron, Ackbar .... 818 Yougottabekiddingme TPK ..(413) 00000000000hhhhh Pleasssseee!

Anyways, as you can see I am now the asshole! And if you had any common decency left in the empty shell that I have just reduced you to, you should politely tell me that you have somewhere else to be, and make for the nearest exit post haste.

But here's the thing..... before you go, let me ask you just one question.

What if it wasn't a person who was presently recounting their weird nonsensical dreams to you? What if instead, it was a mysterious voice from the ether spewing this strange foggy nonsense before your very eyes? Foggy nonsense that was loosely based on the scant few words you had, moments earlier, typed into an unassuming text editor. Foggy nonsense that at the push of a button, mysteriously manifested itself on your screen. Would you find more wonder in these sort of rantings? Could you be intrigued by a bot? One tenuously lilting within a nonsensical haze, blurring the lines between the coherent, the spooky, and the maniacal?

Would that change your opinion of the dreaded dream journal shared?

Well, ever since I stumbled across this blog post a few years back by the author Robin Sloan, I have been able to answer this question for you. And as far as I'm concerned, the answer is a resounding "Yes!"

The project Sloan put together basically combines a few separate tools to create a bot that does just this sort of thing.

The parts:


What little I knew about machine learning back in 2016 was that there was something called Tensorflow that wouldn't run on my Mackbook Air. Book closed. That was until I read Sloan's blogpost and found out there were other tools available that can do some of the machine learning heavy lifting and that might actually run on at least one of my computers after all.

The engine of Sloan's project is torch-rnn. An LSTM (Long Short Term Memory) and RNN (Recurrent Neural Network) tool that can learn from reading huge chunks of text. What does it learn? Well, how to write sentences that more often than not make some sort of coherent sense. The crazy thing is, it builds these sentences not word by word, but rather character by character. That is to say, it doesn't know for example that "The Laser was pointed at the aliens" are separate words that fit together to tell a story, but rather that T-h-and-e often start a sentence together, followed by a space, which often has the letters l-a-s-e-r proceeding, again followed by a space... etc etc.... And how does it know this? Well because Sloan took the time to train torch-rnn on a dataset he compiled of pulp science fiction magazines pulled from the internet archive


So Sloan then took the torch-rnn package and added a couple of bells and whistles to it. Basically creating an api service (torch-rnn-server) that runs in the background on your local machine. When called with an http request, and given the proper parameters, the api then returns a selection of texts generated from any text which was seeded to it. If no text is seeded to it?
Well then it just wings it, more or less.


The final piece is rnn-writer, a plugin for the Atom text editor that reads back a certain amount of characters preceding the text prompt and, using torch-rnn-sever generates predictive text based on that content using a model created by torch-rnn.

Are you still with me?

Well if you are, thanks for bearing with this rambling. And please let me tell you how much fun I've had over the past couple of years installing these tools on my home computers, work machines, and even playing around with them on a Raspberry PI or two.

I've even tried training the RNN on a model of my own using an old macbook pro that has an ancient but CUDA capable nvidia gpu. However, the process was still excruciating slow, even with CUDA acceleration, and the data set I created was a textbook example of what not to do when training a neural network. Basically I set out to confuse the hell out of the learning tools and succeeded magnificently. My data set consisted of a whole bunch of Gutenberg project texts as well as other sources from authors such as Joyce, Eliot, Pynchon, Vonnegut, O'Connor, Wharton, Melville and so on..... Suffice it to say that the resulting model was barely able to spew out a coherent sentence, not to mention only at a rate of about once in every 100 attempts.

But using a sample from Sloan's pre-trained SciFi model, I have had a lot of fun slapping together little stories, poems and robot-dream journals that are now scattered about hard drives in my home, the cloud, and various other places of work over the past few of years.

At a previous job for instance, our daily standups were conducted in Slack. I would append each of my daily entries with a sentence or two of robot-blather that eventually made up this sort of serialized story; a selection from which I've posted to this listed feed.

Another entry in this feed is a more curated tale, again built with the rnn-writer plugin. However, in this case, the story has been composed with a bit more human intervention. Segueing from fragment to fragment, I tried here to use the rnn-output at the skeleton of the tale, but used my own editorial content to create a bit of continuity that the RNN cannot deliver. My goal was not to write any award winning narrative, but rather to nudge the text into a more readable selection, while still maintaining that dream-journal weirdness in the end.

I think that's the main attraction. Whereas my expectations are much higher for any human ranting I might be subjected to an any given day, the mere fact that a neural network can come close to emulating the annoying conversation of a well intentioned, but misguided human is the selling point here.

There already are much more effective neural networks out there that an generate completely readable text. I guarantee you that you have read more than a few news articles, sports reports, weather predictions and have even been suckered into falling for click-bait, all composed by an algorithm posing as a sentient meat sack.

In recent weeks there has been a lot of press attention given to the new GPT-2 neural network tool. I would bet even some of that reporting was bot assisted. But the toolset is being hailed as nearly indiscernible from human generated content, when flexed at it's full capacity. The hype has been that it is so efficient that the developers have decided not to release the full powered version of their work, out of fear for the potential mayhem such a tool could produce in the hands of bad actors.

But even crippled, this tool is pretty astounding.

Take this for example: I fed one of the weirder sentences found in one of the 'stories' I had previously generated with rnn-writer into a GPT2 driven text engine available on line. What follows is the completion:

In the round mirror the robot could see Frances walk over and lick water off the stranger's face. But Frances soon realised they were trying to steal her drink and the robot decided to run away, chasing it through the air.

"The robot couldn't see through, it had to get in there," said Jochen Wüstmer, head of the Robot Safety department at the Swiss Federal Robotics Office.

Instead of just running towards Frances to kiss him, the robot ran alongside her – and when Frances started to push against it, the robot turned and smashed into Frances, breaking her hand in the process.

"We decided to go into rescue mode: to go into rescue mode because the robot could not move itself properly," said Wüstmer.

Fris and Jochen Wüstmer: Swiss team have one robot for the whole world to worry about Read more

Frances told reporters the robot was unable to communicate properly with her partner during the assault, so when Jochen took over as team manager, the robot now lives with Frances and will remain behind her apartment in the Swiss canton of Rheims.

The incident happened on 22 March, while Frances was getting ready for work at a Swiss grocery store, where she was looking after the children of one of her employees, according to reports.

Even though it still has the dream-journal quality, the continuity is much more impressive than any text generated by torch-rnn. This new learning model now has a modicum of an attention span. And what I found particularly interesting about this example, is how the text generated seems to bounce between a literary and a journalistic style.

I may have to scrape and scrounge my pennies now in order to purchase a more powerful CUDA capable machine. Then I might just try to train GPT-2 with my trick-the-robot corpus of sundry and vastly different authors. What might be the result? I'm hoping it would generate exquisite-corpse like text, as if a folded page was passed from Flannery O'Connor to Albert Camus, to Kurt Vonnegut, to T.S. Eliot.

"I don't believe in anything. I want to stay as close to the edge as I can without going over. Out on the edge you see all kinds of things you can't see from the center. I assure you that it's better to sleep with a sober cannibal than a drunk Christian, for only those who will risk going too far can possibly find out how far one can go while Talking of Michelangelo. "

I'm presently waiting on the delivery of a new AI driven Generative Text project of Sloan's which uses the new GPT-2 learning model in conjunction with some other bits of software which he has tinkered together. The crux of this project is that everyone who orders a copy gets a unique work based on their answers to a survey, some intermediate software developed by Sloan, and the ranting of the GPT-2 having added a corpus of fantasy fiction to it's existing model built on scraped internet text.

Well, anyhoo, before you leave, why not watch a short film that was written using a torch-rnn like tool trained on a bunch of scifi scripts.

Sunspring | A Sci-Fi Short Film Starring Thomas Middleditch

Because: The Internet!

Also, I highly recommend reading Robin Sloans novels, Mr Penumbra's 24 Hour Bookstore and Sourdough. Both are delightful reads. A bit Sci-Fi, a bit Mystery, yet they never lean so heavily on genre tropes as to not primarily just be fun and charming stories in their own right.

Waiting With Pictures In Her Mouth

The Robot and Frances:

The old robot had once thought that it was a man. But in fact, it had just been a prisoner of the old days. Those days, back when it served as a stenographer for the State. She had been here, for most of this time, as a part of that Project.

For past few hours however, it had been waiting. Waiting for Frances to finally say something, while pictures of faces gently scrolled across the display situated where one might expect it's mouth to be.

When she did finally speak, it was to say, "It is the burden of having an arm that is still".

She thought this might make the robot smile... Could this robot smile?

"One constructed of confusion and sweat." retorted the robot. "It could be different though. I could be a lie. But I think there is a detachment when we meet our sinners." at which the scrolling faces began to iterate rapidly as they trended with more troubled expressions.

Is that what a robot smile looks like?

Frances smiled and/or frowned. Sometimes the robot had difficulty differentiating the two. She never was good at reading human faces.

"And you, sir," Said Frances "You're a hard woman."

The stranger:

The view outside the window, where the dials vanished, was of the sky, pouring across the pathway. From the stranger's perspective on the far side of the room however, it was merely a trifle. He groaned as he shifted to a sitting position.

In the round mirror the robot could see Frances walk over and lick water off the stranger's face.

The robot wheeled around. It was time to embark.

Earlier, the stranger had sat down at the top of a corridor. Burdened with an elusive thought, he instead remembered the whaleboat which was now lost to the stars.

What if I am too close to it? he asked himself. What if there were no more paralysis? What if they were human?

The whole thing was a fine bird. A separate voice in his head retorted. A message from the place where they dipped their feet into the darkness.

It was less a statement, than it was a promise. A hint that there might be a way to accept it. What kind of nonsense is that?

What has happened to me?

As he remembered this, ears still ringing, he shook his head. Who was it who said "Acceptance is a horrible little catapult"?

The robot raised it's eyes. It could read his uneasiness.

"I'll try to make it quick!" it chirped.

Owling and Bonnie:

Meanwhile in the Rest Stop, there was a lovely man who had fallen in love with a stewardess. He was discreet, and she was silent.

Owling opened his eyes. "They may just be a better contact," he said to Bonnie. "But I suppose there aren't any second services. Not on that kind of ship"

Bonnie nodded half-hurriedly. "I have something I want to share with you."

She held out a chip. It was an old release, one from a few years back. A micro single by the Some New Electrical Stuff.

"I remember these guys!" said Owling. "They slept on my lawn after they listened to the lights. They liked to be outside that way."

He squeezed the chip and it began to play.

Don't be angry, dear.
Don't be like that when the story has changed.
Don't be surprised at the truth.
Don't be so sure, you know.

Speak to the natives. Maybe they're not so stupid after all.
Sing of the beginning of an electronic ball,
That's all.
That's all.
That's all.

They smiled, each in their own way, then set out on a walk. Intent on winding between this rest stop and the range of the lake, feeling as if they were one with the scene of this country.

She again looked at him, this time without saying anything. But there's a difference, she thought, Only it was left along the way. Along with a whole other story. It was part of the truth that has yet to be found.

When they reached the far end of the hill, they found the robot waiting for them, with their pictures in her mouth.

Before the Transporter Fell

Today the robot said that the one thing in the world was hidden.

The others were gone. But it was hard to know what was coming, so much there.

The sound of his face spilled out and he was silent for a moment on his feet.

"Oh, I don't have to see you, Steve. What can I do for you?"

"I don't know. I'm not sure."

"I can see that you can see better for yourself."

A sudden mud beam broke out of the cargo panel and led the way to the porch. It was a rich one, but torn around in the corners of the lake.

"I have the transmitter." She had to sit still, just exactly the same, apparently in this case, and his nose was empty.

"It isn't the thing that can be left," he said.

"It's a funny good idea, but you don't have to like it. After all, we don't have the same answer as before."

"But what is it?"

"I don't know. I'm afraid I can't see you in the first place."

Beyond the stars the scout passed and started to climb.
He gained a few drinks and sprang to move. In front of him the incomprehensible sound started. But inanimate things ask questions, and many of them are rare. They know nothing about their people. Nobody kills anyone. They don't want to take some alien menace to the sea. You imagine there are others. Will you be so sure of the mental projection of your body? Can you laugh on the radio now?

"I couldn't help it."

"You can't do anything," he said. "I can remember that too much, and I don't think you're not a plant. "

"The computer is almost ready for it," said the commander. "I am a bit abandoned on this planet."

"And what are you doing here? What have you done? What is this place?"

"I don't know," Old Tom said. "It's a little stronger than I can see."

He stared at the table top. "The story is a strange problem. I felt that I would be tempted, and it would be a certainty. I was going to say something impossible, so I looked at it and thought about it. As it was, I felt the anger of relief. But I was not interested, until the lady gave me a question. A single song had squeezed it into my sleeve, when the monkey suddenly rose to my arm and raised my hair there. The question was almost an accident. It lilted across the desert to the mountain. There it was shared with old friends and horses, who took it into the bellies, using the stuff on their roads. They were all so busy about the place. I was sure that I was there now. There was only one chance -- and then there was a ship on the bank.

So what was the place?

It was a special kind of house where the grass was transparent.

He made a grim peculiar joke. He turned to Olga. "I know, Mercer,"

"I want to make the sound of it more than it can -- " He didn't even know what he had felt.

He hadn't changed his mind when he tried to do something about it, but he couldn't be less interested in it.

"We made it. They ate, and the big boys were all telling me about them."

"They wouldn't be normal enough,"

A moment later, the transporter began to fall.