My favorite bot!

... and other AI projects that spark joy

annie rauwerda
November 03, 2021

null

I’m Annie Rauwerda, and I started @depthsofwikipedia on InstagramTwitter, and TikTok to highlight my favorite trivia and internet rabbit holes. I partnered with Bullish Studio to launch this newsletter. While most editions involve Wikipedia deep dives, today I'm interviewing the creator of my favorite Twitter bot, @ResNeXtGuesser! Here's my favorite quote from our conversation:

"In my opinion, the funniest and best projects are those where you take some highly professional, advanced, or academic subject/technology and throw in a great deal of immaturity."

First, some AI-related links I like!

null

Bots you like! 

You're about to meet my favorite twitter bot, so here are the bots that you recommended in my Instagram story question box.

  • @NYT_first_said was the most requested, which makes me so happy. It was created by my friend Max. The bot tweets when a word is published in the NYT for the first time. Some notable recents are ‘cleanfluencer,’ ‘momcore,’ and ‘sl*ts.’
  • @wiki_tmnt posts Wikipedia titles that can be sung to the Teenage Mutant Ninja Turtles theme song. The bot has been defunct for a few months, but you can scroll through the old posts. 
  • @deletedwiki posts ridiculous deleted Wikipedia titles 
  • @NFL_Scorigami is my boyfriend's favorite, and even though I don't love watching football, I can appreciate the enthusiasm over first-ever final scores in the NFL!! 
  • @JoelDongsteen tweets about dongs in the style of celebrity pastor Joel Osteen. For some reason, almost 40k people follow it.  
  • Emote! At the Location. Go mad! At the grocery store. Dissociate! At the chess tournament. @EelectricMiguel is an electric eel at the Tennessee Aquarium who can trigger tweets, which say things like ZAP!!! and ZING!!! 
  • @aceCourtBot exploded to 386,000 followers for animating Twitter conversations into Ace Attorney court cases.

ICYMI

Interview with neural net guesses memes

The account's creator is a 23-year-old embedded computer engineer in San Francisco. He prefers to keep his professional life separate from his online life, so I'm using Dave in place of his real name (nod to the Dave Rule). 

A few days ago, I discovered the delightful @ResNeXtGuesser bot, which tries its hardest to make sense of memes. When given bizarre, cursed images, the bot labels the photo's contents — sometimes with hysterical inaccuracy. When I scanned the Github code (available at this link), I realized that the program only gives 1,000 categories of images, which explains why the bot seems so creative with its classifications. 

 I asked the account's creator to answer a few questions about his internet masterpiece, and in the few days since I first reached out, the account's following has EXPLODED. In the past day alone, it has gained 20k followers, and it's almost to 100k. I'm so excited to share the interview.

Annie: When did you start @ResNeXtGuesser? What inspired you to create it? 

Dave: I launched the account in June of this year. I recently graduated college, and although AI and machine learning weren't my main area of focus, I was really interested in the subjects and had taken a handful of classes on them. I now work as an embedded computer engineer, so I never even come close to dealing with machine learning. I wanted to do a project that gave me a chance to play with neural networks (NNs) again.

In my opinion, the funniest and best projects are those where you take some highly professional, advanced, or academic subject/technology and throw in a great deal of immaturity. In college, I had various AI/ML assignments that dealt with classifying images, and it was so funny to me to see what happened when I sent through bizarre or random memes. What was particularly interesting was that even though the NN got it wrong 99% of the time, you could often see/understand what the NN was thinking or why it came up with its prediction.

I recently learned about the ImageNet competition, and how neural nets are already better than humans at predicting the contents of an image. But the problem is that those NN's are tested using boring images, such as cats, dogs, cars, pencils, etc. I made a video on my youtube account putting random memes through the ResNeXt NN to see what happened. In my opinion, the results were really funny. A couple months later, I thought that running memes through a NN would make for a really entertaining Twitter bot, so I got to work on it.

Annie: How long was the programming process? What were the main steps of the project? 

Dave: The programming process was actually quite quick — I'd say it took me maybe a month of half-hearted, over-the-weekend type work. There are a lot of pre-existing Python libraries that make interfacing with the twitter API a lot easier. Besides the Twitter stuff, the Python library PyTorch provides a bunch of pre-trained, ready-to-use NN models that are super easy to get up-and-running. Ironically, for a bot about neural networks, the neural network code was the easiest part.

The real pain was automating grabbing submissions through the DMs. Twitter's documentation on the subject is quite sparse, and the libraries I was using to interface with Twitter had even worse documentation. But I got it in a usable state, albeit with a handful of bugs. But now, the account has exploded in popularity, which I am so happy to see. However, the high volume of DMs causes my code to send so many API requests that I hit the request limit and Twitter times me out, which breaks my code.

Annie: You work in embedded computer systems, you create Twitter bots and Youtube videos, and you like memes. Do you have any other hobbies?

Dave: I love working on personal projects. Right now, I'm working on getting a website up and running. It's fun! I like learning new things, and it gives me a chance to make neat stuff. I love cooking and photography (possibly the only two "artistically creative" things at which I'm somewhat competent). And I'm really into stocks & finance — I'm a huge math nerd, and quantitative finance is neat to me.

Annie: What are some things on the internet you’ve enjoyed lately and would recommend to others? 

Dave:

  • I used to be really big into OS development, and the OS Dev Wiki is such a massive treasure trove of information for anyone interested in the subject. Every now and then, I'll get lost going down rabbit holes on the site.
  • Cat-v.org is another interesting site. It's a group dedicated to preserving and supporting the old Plan 9 Operating system. Their website has a lot of fun stuff to look through. It's a lot of really old-school, UNIX-purist type content, and I love it.
  • Pointlesssites.com is such a favorite of mine. It's a site that aggregates pointless websites. There's some fun stuff on there!

Annie: Do you have any favorite Wikipedia pages? 

Dave: Absolutely! I'm a Wikipedia junkie which is why I love your account. Here are four in particular:

  1.  Dishwasher Salmon: It's funny
  2. Toast Sandwich: The British equivalent to dishwasher salmon
  3. Complaint tablet to Ea-naser: Possibly my favorite random piece of trivia. It's an ancient clay tablet from 1750 BC that is the oldest known customer complaint, directed towards a merchant whose copper was low quality.
  4. Tabun (nerve agent): I don't think the topic of chemical weapons is humorous, but Wikipedia describes this nerve agent as "tasteless with a faint fruity odor". I found this funny because of the implication that some psycho drank it and lived (long enough) to describe its taste and smell.

Annie: Thanks again for answering these questions, and best of luck as you keep working on computers, working on bots, and collecting cursed images!! 

That's all for today! As always, feel free to forward this to a friend and send your thoughts to [email protected]. I really like your emails! 

Subscribe to Depths Of...

Deep dives into Wikipedia rarities, curated by @depthsofwikipedia

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.