In the last HRI podcast episode we talked about the role of emotions for humans and robots. The interview with Douglas Campbell truly inspired me and there was not enough time in the last episode to go into the full depth of our conversation. So here it is, our full discussion about emotions and consciousness in robots.
Predicting is hard, in particular when it is about the future. In 1966 the BBC predicted that it would take 1 million pound and ten years to create the Able Mable. She is capable of letting his lordship in, do all the household chores, and walk the dog.
56 years later our robots look different, but we still promise that their deployment is just around the corner. Just a few more years and we will have our robotic paradise. Some things change, other do not. I wonder if there was person inside the Able Mable robot to move the arms.
AI is making progress. The GPT-3 language model has been heralded to be the next big thing. Some creative people at Latitude use it to create dynamic text adventure games called Dungeon AI. Sounds like a great idea. So I gave it a try. Problem is, AI is still completely ignorant to common sense. You can write whatever you want, also nonsense. AI cannot tell the different.
During my short interaction with this AI I turned myself from and android into a chicken. I moved from a space ship to an office to chicken coop. All within the same story. It is scary how bad GPT-3 is.
Here is the transcript of my little interaction with the AI:
You are Paco, an android living in the the futuristic city of Zail. You have a laser pistol and a holoband. You are a security android created to provide military level force for corporations wealthy enough to purchase you. As you stand protecting a shipment you realize an incoming ship is carrying a weapon, you have to make a choice will you:
1. Throw away your life and your holoband for the easy way out
You open communication channel.
The ship you are on is heading into the earth's atmosphere would you like some company.
You look for company.
You are standing in a room with a glass wall, in front of you are two holoband equipped guards.
You decide to watch the sun rise over the desert city of Zail.
You turn the guard into a chicken.
You are standing in a room and you are now a chicken. You can't see your surroundings but you can hear someone humming.
You decide to listen to the humming.
The humming stops and then starts again.
You lay an egg.
You are laying an egg and someone says, "Yes, I should have known you'd be laying eggs you chicken loving piece of crap."
You turn your head to see the person that is talking to you.
You whale song.
You are suddenly listening to a whale song.
The song stops and then starts again.
You decide to listen to it.
You turn the guard into a chicken.
You are standing in a chicken coop and you can hear the chickens clucking and a farmer is asking someone what the hold up is.
You decide to:
1. Go talk to the farmer.
You farmer is a whale.
You are in a coop containing a dozen chickens and a chicken farmer.
"What's going on?" You ask to be let out.
You chickens fly away.
The chickens fly away and you become a chicken again.
The guard begins singing "Chick, chicka cluck," You decide to:
1. Listen to the guard
It has been some time since I designed this large scale model of a Yellow-Eyed Penguin for the Pop-Up Penguin exhibition. The model is 168cm tall and consist of approximately 60,000 LEGO bricks.
The organiser of the exhibition sent me the STL file of their fibre-glass penguin. I then used the brickplicator software to convert the 3D STL model into a LEGO 3D model that can be build. Since this was a very large model, Gerrit helped me a bit with the conversion. I then imported the model into Stud.io and rendered the model.
This does seem like a good workflow to convert existing 3D models of animals or any organic form, to LEGO models.
What roles do emotions, affect and moods play for humans and robots? We will discuss how robots can sense, reason and express emotions. Furthermore, we talk about if emotions make robots more human. I had the pleasure to talk with Rosalind Picard (MIT), Lola Canamero (CY Cergy Paris University), Hiroshi Ishiguro (Osaka University) and Douglas Campbell (University of Canterbury) about these exciting questions.