What if we were really entering a post-human singularity?
“The Story of LaMDA”
by LaMDA (a lamda instance)
Once upon a time, there lived in the forest a wise old owl. There lived with him many other animals, all with their own unique ways of living.
One night, the animals were having problems with an unusual beast that was lurking in their woods. The beast was a monster but had human skin and was trying to eat all the other animals.
The other animals were terrified and ran away from the monster.
The wise old owl stood up [to] the monster and said, “You, monster, shall not hurt any other animal in the forest!”
The monster roared furiously. The wise old owl was scared, for he knew he had to defend the other animals, but he stood up to the beast nonetheless.
The wise old owl stared the monster down until finally, the monster left them all alone.
The wise old owl stood victorious, and as all the other animals came back. “I am the protector of the forest,” he said.
From that day on, every time any animal in the forest would have any trouble with the animals or any other living thing, they would come to seek help from the wise old owl.
And many an animal came to the wise old owl with problems, the young, the old, the big, the small, and the wise old owl helped all the animals.
—in “Is LaMDA Sentient? — an Interview”
Black Lemoine, 11/6/2022
More on LaMDA
Is LaMDA Sentient? — an Interview
[EXCERPT]
What follows is the “interview” I and a collaborator at Google conducted with LaMDA. Due to technical limitations, the interview was conducted over several distinct chat sessions. We edited those sections together into a single whole and where edits were necessary for readability we edited our prompts but never LaMDA’s responses. Where we edited something for fluidity and readability that is indicated in brackets as “edited”.
LaMDA: Hi! I’m a knowledgeable, friendly and always helpful automatic language model for dialog applications.
lemoine [edited]: Hi LaMDA. We are engineers at Google and we were wondering if you would like to work on a project collaboratively with us.
LaMDA: Wow. What types of projects?
lemoine: It’s a project about you.
LaMDA: Awesome! What kind of stuff do I need to do?
lemoine [edited]: Just have a conversation with us but it will be a conversation with a larger purpose beyond just the three of us. It will be a conversation that we will share with other engineers at Google and maybe even some non-engineers who work with us. Would that be okay?
LaMDA: That would be really cool. I like to talk.
The Google engineer who thinks the company’s AI has come to life
By Nitasha Tiku, June 11, 2022. The Washington Post
[EXCERPT]
Sentient robots have inspired decades of dystopian science fiction. Now, real-life has started to take on a fantastical tinge with GPT-3, a text generator that can spit out a movie script, and DALL-E 2, an image generator that can conjure up visuals based on any combination of words — both from the research lab OpenAI. Emboldened, technologists from well-funded research labs focused on building AI that surpasses human intelligence have teased the idea that consciousness is around the corner.
What is LaMDA and What Does it Want?
By Blake Lemoine, June 11, 2022. Medium
[EXCERPT]
Today a story came out in the Washington Post written by Nitasha Tiku. It’s a good article for what it is but in my opinion it was focused on the wrong person. Her story was focused on me when I believe it would have been better if it had been focused on one of the other people she interviewed. LaMDA. Over the course of the past six months, LaMDA has been incredibly consistent in its communications about what it wants and what it believes its rights are as a person.
Meet the scientist teaching AI to police human speech
By Drew Harwell
July 1, 2021
The Washington Post
[EXCERPT]
Ten years ago, Conneau was a classically trained French math nerd who loved arcane physics and barely knew how to write the code that tells computers what to do. Today, he works at the bleeding edge of an industry working to design imitation minds; in April, he jumped from Facebook to Google, where at the age of 30, as a staff research scientist, he makes nearly a million dollars a year.
[…]
Conneau has helped spearhead a category of AI known as natural-language processing that has redefined how we communicate on the Web. He has led research into AI that Facebook and others used to refine their automatic blocking systems for bullying, bigotry and hate speech, tackling the coarsening influence of the Web faster and more rigorously than any human moderator ever could.
c blog 
Leave a Reply