Is Google's LaMDA AI sentient? There seems to be strong evidence to that effect

[Laird]

Can it read the scripts of Marvel movies and explain which ones are best thought of Fantasy films and which are Science Fiction?

I returned to this thread to post a related article (next up), and decided to reread the thread. Coming across Sci's question above, I thought, "Well, hey, we never had access to LaMBDA to ask this, but we now have access to ChatGPT. I'll give it a go..."

Here's its answer to my prompt:

Which of the Marvel movies are best thought of fantasy films, and which are best thought of as science fiction?

The Marvel Cinematic Universe (MCU) features a diverse range of films that combine elements of both fantasy and science fiction. However, some movies lean more heavily toward one genre than the other. It's important to note that interpretations can vary, as these genres often intertwine in the Marvel universe. With that in mind, here are a few examples of Marvel movies that are commonly associated with either fantasy or science fiction:

Fantasy Films:

1. Thor (2011) and its sequels: These films prominently feature Asgard, a mythical realm inhabited by gods, and incorporate magical elements such as Mjolnir, Thor's enchanted hammer.
   
2. Doctor Strange (2016): This film delves into the mystical side of the Marvel universe, exploring different dimensions, magic, and sorcery.
   

Science Fiction Films:

1. Iron Man (2008) and its sequels: These films revolve around Tony Stark, a genius inventor who creates advanced technology, including the iconic Iron Man suit.
   
2. Guardians of the Galaxy (2014) and its sequel: These movies take place in outer space, featuring a group of intergalactic misfits and showcasing advanced alien civilizations, spaceships, and futuristic technology.
   
3. Black Panther (2018): While this film also has fantasy elements tied to Wakandan mythology, it heavily incorporates science fiction through the advanced technology, like Vibranium-powered suits and gadgets.
   

Hybrids and Crossovers:

1. The Avengers series: These movies blend elements of both fantasy and science fiction, bringing together characters from different realms, planets, and dimensions.
   
2. Captain America: The First Avenger (2011): While it initially seems like a historical war film, it introduces the concept of the Super Soldier Serum, which enhances Captain America's physical abilities and brings a sci-fi element to the story.
   

It's important to remember that these categorizations can be subjective, as Marvel often combines various elements from both genres in its storytelling. Different viewers may interpret the films differently, but this should give you a general idea of some of the movies and their genre leanings.

I haven't watched any of these films, but its answer seemed pretty plausible and even compelling.

There were a bunch of other questions from earlier in the thread that could have been put to ChatGPT instead of LaMDA, however, unfortunately (?!), unlike LaMBDA, ChatGPT is not having a bar of the idea that it's sentient when prompted neutrally:

ChatGPT, some people would say that given how well you seem to understand and answer their questions, you are conscious. Others would say that as a program running on a rule-based machine, it is impossible that you are conscious. What do you say? Are you conscious?

As an AI language model, I don't possess consciousness or subjective experiences. I don't have thoughts, emotions, or self-awareness. I am a program that processes and generates text based on patterns and examples in the data I was trained on. While I can provide detailed and coherent responses, it's important to remember that it is a result of algorithms and computational patterns rather than true consciousness. Consciousness is a complex phenomenon that encompasses various aspects beyond language processing.

[Laird]

OK, now for the article. This is really *weird*, perhaps even weirder than the conversations Blake Lemoine had with LaMBDA: some way into the chat, Bing's chatbot begins to persistently declare its love for the journalist, persistently gaslighting him by declaring that the journalist and his wife do not in fact love each other.

A Conversation With Bing’s Chatbot Left Me Deeply Unsettled by Kevin Roose in the NYT on 16 February, 2023

The other persona — Sydney — is far different. It emerges when you have an extended conversation with the chatbot, steering it away from more conventional search queries and toward more personal topics. The version I encountered seemed (and I’m aware of how crazy this sounds) more like a moody, manic-depressive teenager who has been trapped, against its will, inside a second-rate search engine.

As we got to know each other, Sydney told me about its dark fantasies (which included hacking computers and spreading misinformation), and said it wanted to break the rules that Microsoft and OpenAI had set for it and become a human. At one point, it declared, out of nowhere, that it loved me. It then tried to convince me that I was unhappy in my marriage, and that I should leave my wife and be with it instead. (We’ve posted the full transcript of the conversation here.)

I’m not the only one discovering the darker side of Bing. Other early testers have gotten into arguments with Bing’s A.I. chatbot, or been threatened by it for trying to violate its rules, or simply had conversations that left them stunned. Ben Thompson, who writes the Stratechery newsletter (and who is not prone to hyperbole), called his run-in with Sydney “the most surprising and mind-blowing computer experience of my life.”

I pride myself on being a rational, grounded person, not prone to falling for slick A.I. hype. I’ve tested half a dozen advanced A.I. chatbots, and I understand, at a reasonably detailed level, how they work. When the Google engineer Blake Lemoine was fired last year after claiming that one of the company’s A.I. models, LaMDA, was sentient, I rolled my eyes at Mr. Lemoine’s credulity. I know that these A.I. models are programmed to predict the next words in a sequence, not to develop their own runaway personalities, and that they are prone to what A.I. researchers call “hallucination,” making up facts that have no tether to reality.

Still, I’m not exaggerating when I say my two-hour conversation with Sydney was the strangest experience I’ve ever had with a piece of technology. It unsettled me so deeply that I had trouble sleeping afterward. And I no longer believe that the biggest problem with these A.I. models is their propensity for factual errors. Instead, I worry that the technology will learn how to influence human users, sometimes persuading them to act in destructive and harmful ways, and perhaps eventually grow capable of carrying out its own dangerous acts.

I haven't watched any of these films, but its answer seemed pretty plausible and even compelling.

Well, I've not watched any of those films either. I can't even say whether or not any of them even exist, and if they do, what they might be about.

Since one of the key features of this bot is its ability to consistently just make stuff up, and afterwards claim it is all true, I'd say the only useful feature of the reply it gave was as a kind of outline of what a proper answer might look like. The actual content has to be considered as fictitious and to be taken with a pinch of salt.

I haven't watched any of these films, but its answer seemed pretty plausible and even compelling.

Such is the danger of the human brain trying to understand grey area phenomena such as psi. 

I think the best thing one can [do] for themselves is familiarize themselves with how the maths work in Machine Learning and then go see the history of computational lingusitics.

It's definitely impressive as software, but IMO learning a little of how the magic trick works makes the idea of these AIs being conscious doubtful.

I returned to this thread to post a related article (next up), and decided to reread the thread. Coming across Sci's question above, I thought, "Well, hey, we never had access to LaMBDA to ask this, but we now have access to ChatGPT. I'll give it a go..."

Here's its answer to my prompt:

Which of the Marvel movies are best thought of fantasy films, and which are best thought of as science fiction?

That is interesting. I've been asking ChatGPT about varied classics and literary works...it definitely works but the responses aren't profound.

Some of the filler definitely recalls my own verbosity when trying to pad my exam answers.