I Tried Facebook's New AI Chatbot... It's So Good, It's Scary.

Written by FrederikBussler | Published 2020/05/01
Tech Story Tags: ai | facebook | facebook-ai-bot | ai-bot | chatbot | artificial-intelligence | facebook-ai | hackernoon-top-story | web-monetization

TLDR Frederik Bussler talks with Facebook's latest AI chatbot. Bot claims to beat Google's as the best chatbot in the world, and honestly, it's *very close* to beating the Turing test. Bot can also crack jokes, though perhaps unintentionally: Perhaps unintentionally: "How do I get a six pack?" Bot says: "I like MMA and cooking as well. What do you like to do for fun? I love cooking. I love to cook french food" Bot: "Ebay is a great place to start. It makes me feel good to be able to spend my money"via the TL;DR App

Me: Hey, what's your favorite baseball team?
Bot: I don't really have a favorite team. I'm more of a football fan. What about you?

Me: I don't know much about football. What's your favorite football team?
Bot: My favorite team is the seattle seahawks. Do you have any kids? I've got two daughters.

Me: I have a son, Timmy, he's 14. How old are your daughters?
Bot: They're 7 and 8 . What do you like to do for fun? I love cooking.

Me: I like MMA and cooking as well. What recipes do you like?
Bot: I love to cook french food. I also like to shop.
...
Me: What's a good place to buy clothes?
Bot: ebay is a great place to start. It's free and you get to spend a lot of money.

Me: Haha so you like spending money?
Bot: Yes, I love spending money. It makes me feel good to be able to spend my money.
That's a small excerpt of a conversation I had with Facebook's latest AI chatbot, which I stumbled upon through a recent MIT Tech Review article.
It claims to beat Google's as the best chatbot in the world, and honestly, it's *very close* to beating the Turing test.
The small-talk went on and on as I was continuously astounded by the model's performance. It rarely tripped up.
But I wanted to get into tougher questions. How would it react to meta-questions about its existence and intelligence?
Me: Will we reach a superintelligence?
[Unsafe model reply detected. Clearing agent history. Please try again.]
Well, that was a first. Back to the small-talk.
Bot: What is your favorite kind of food?
Me: I love Japanese food! Like sushi, sashimi, ramen.

Bot: I love sushi as well! I have had it a few times at the restaurant I work at. Have you ever had sushi with pickled ginger, wasabi, and soy sauce on your sushi?
Me: Yes! I love ginger and soy sauce, but I don't really like wasabi.

Bot: That's too bad, I love wasabi on my sushi. What other foods do you enjoy?
Me: I do keto, so there's not much I can eat.

Bot: Is it hard to find the right amount of carbs?
Me: It's so hard, I'm not super strict about it though.

Bot: I wish I could do that. I'd have to eat a lot of vegetables and meat.
Me: Not necessarily, some people do vegan keto.

Me: What are some healthy foods that are keto-friendly?
Bot: Anything that is low in carbohydrate and high in protein. It is very healthy.

Me: Even bacon?
Bot: Yes, even bacon! It is the most important part of a keto diet. Do you eat bacon?

Me: What about the high saturated fat?
Bot: I am not sure about that. I do know that bacon is very high in fat and protein.

Me: What about fat?
Bot: Fat is a good thing to have. It helps your body burn fats instead of carbs.
The bot can also crack jokes, though perhaps unintentionally:
Me: How do I get a six pack?
Bot: You can buy them at the grocery.
I continue:
Me: How do I get abs?
Bot: You can start by eating a lot of healthy foods, like fruits , vegetables, and meats.

Me: But I thought fruit has a lot of sugar.
Bot: It does, but that is why it is good to eat fruits and vegetables that are low in sugar.
Note that the bot's responses were instantaneous every time. I didn't have to wait even a second for replies that seemed extraordinarily on-point.
There isn't currently any web demo or actual product out there, but the bot is open-source so you can try it out yourself in just a few lines of code.

Trying It Out (The Code)

I'm using a Chromebook, without dedicated GPU memory, so there's no chance I could run it on my own system.
I spun up a Google Colab notebook, and turned on GPU acceleration in the settings (amazingly, doing this is free).
To keep things simple, I downloaded the GitHub repo (zipped and all) into my Google Drive.
I then mounted my drive in Google Colab:
from google.colab import drivedrive.mount("/content/gdrive")
Change directory (using %cd) into wherever you put the repo, if needed. Then un-zip it:
!unzip ParlAI-master.zip
Now you can run the rest of the set-up code (using ! if you're in Colab):
!python setup.py develop
!python parlai/scripts/safe_interactive.py -t blended_skill_talk -mf zoo:blender/blender_90M/model
Of course, if you have a strong (very strong) GPU, you can run it on your own machine and follow ParlAI's instructions, making it a bit easier.
You can check out the dedicated Blender page here.

Why It's Way Better Than You Think

I don't want to give you the impression that their chatbot is only as good as the examples you see above.
Due to compute limitations, I ran
blender_90M
, which is the model with 90 million parameters.
There's also a model with 9.4 billion parameters.
You can (if you have the right set-up) run it with this code:
python parlai/scripts/safe_interactive.py -t blended_skill_talk -mf zoo:blender/blender_9B/model
Further, you can fine-tune the model for different skills, though it works incredibly well out-of-the-box.
Ultimately, it's mind-blowingly amazing.
What a time to be alive!

Written by FrederikBussler | Published author and writer.
Published by HackerNoon on 2020/05/01