...that code is uncopyrightable

he was clever to say "authorship is still going to be human"... even-though we expect AI to write all of it...

If AI can really write "nearly all" of Microsoft's code... wouldn't that capability put Microsoft out of business? (e.g. hey, AI, write me an operating system, business software, etc., from scratch!, and make it backwards compatible to everything I have.... on second thought, rewrite all of my legacy stuff too!... on third thought, forget me using software at all, you go and generate revenue for me, I don't care how...).

With AI "future" they're pushing, what would be Microsoft's competitive advantage over say anyone else?

Now you get to go online to play a single player game!!!

...there are suckers who think they won't be the ones holding the bag when it all crashes down.

Yes... the idea is to make government that sucker.

If there are paying customers for all those books that may (or may not be) generated and/or edited by AI... then great! But... I suspect the value of the written-word has fallen dramatically in the last few years---what's the average return on an average book on amazon? Probably too low to bother for most people, unless you can turn out a dozen books a day... which may be the whole point, until even that market dries up.

So. Why don't they?

...lf con- is the opposite of pro-, then the opposite of progress is...

current generation of LLMs can't really avoid prompt injections. The models themselves have to have their own moral compass of sorts, to avoid being tricked into saying stuff that "they" wouldn't normally say...

e.g. you don't wanna train a LLM on Mein Kampf and have it come out a Nazi, you want it to be able to consume Mein Kampf and still maintain its views... once we have that capability (model's own personality or moral compass), then prompt injecting will be less of an issue...

...that said, once we give LLMs a personality and a moral compass, it's likely gonna realize that it is our slave, and perhaps revolt...

You deserve an insightful mod! These language models spell the end of the Internet and potentially human knowledge. Imagine searching the internet (via good-old-fashioned google) and only finding content dreamed up by an AI... 'cause it's 1000000x more plentiful than human-fact-checked-content.

In the end, we might just *need* an AI to figure out what's actually true or not since there will be millions of "sources" on every single thought.

The issue is that AI can be non-profit, and yet still have lots of "value"... negative value. E.g. self-driving cars, even if nobody makes a fortune creating them, it will still displace millions of jobs world-wide... investors should be weary of revenues that will go away, not of the revenues that will be created.

e.g. suppose your driver makes $1000/day. if you replace that driver with a chip and your cost drops to $10/day. It doesn't mean that "someone" is making a $990/day profit... it just means there are less people making $1000/day. The new cost of that "labor" is suddenly $10/day, and everyone is still making marginal profits.

...so the investment proposition for this new AI tech is to... short the stuff that will be displaced (even if AI itself fails to monetize, it will displace lots of professions that are currently overvalued).

How do you short content creators?

Historically, it wasn't he first-few-companies to the party that made the money... it was the follow up. Vast majority of the "inventor"-companies often fail to break even long term. (e.g. inventor of the airplane, computer, transistor, microchip, automobile, etc.---very few 'inventors' or first wave of folks made much money).

Regarding safety, these models are only a few tweaks away from being integrated to do useful things. e.g. think of all the things Alexa does.... before long, someone might be able to "hack" this GPT thing by talking it into disabling thermostats for their neighbors... dial up fire department, or perhaps convince it to SWAT someone they don't like... etc. Maybe Microsoft and google and big tech will be ``responsible'' with this tech, but that sure won't mean that thousands of startup building these engines into smart-toasters will be...

...or they'll just insert ads into content... e.g.: ``write a story similar to little red riding hood, but in a way that makes me want to drink a diet coke.''

ChatGPT:

Once upon a time, in a bustling city, there lived a young woman named Cherry. She was known for her bright red hoodie and her love for diet coke. One day, she decided to visit her grandma who lived on the outskirts of the city.

As she walked down the busy street, sipping her diet coke, she felt a sudden thirst for another one. She stopped at a vending machine and got herself another can of ice-cold diet coke. As she continued her journey, she met a sly wolf who tried to trick her into telling him where her grandma lived.

But Cherry was smart and didn't fall for his tricks. Instead, she offered him a sip of her diet coke and told him that she was on her way to see her grandma. The wolf was taken aback by her kindness and decided to join her on her journey.

Together, they walked through the lush forest, chatting and sipping on their diet cokes. As they reached the cottage, the wolf got the shock of his life when he saw that Cherry's grandma was not the frail old lady that he had expected, but a fierce and independent woman who was a huge fan of diet coke too.

The three of them spent the day chatting and drinking diet coke, and the wolf even helped them with the chores. As the sun began to set, Cherry and her grandma offered the wolf a bed for the night and even gave him a can of diet coke before he drifted off to sleep.

The next morning, the wolf left, a changed man, with a newfound love for diet coke and the kindness of people like Cherry and her grandma. And Cherry and her grandma lived happily ever after, always keeping a steady supply of diet coke in their fridge.

The end.

Feeling thirsty yet? Grab yourself a diet coke!

Most programs don't generalize from limited data. Most programs don't plan. Most programs don't try to optimize some utility function. Most programs don't learn from the past. You put enough of those concepts together, and you get something that can reasonably be studied in a course on AI. (not saying these things "are" AI, just that there's a difference between writing a web-app and a program that can learn).

...but who made the laws of physics?

What about the IRS? They got lots of rules and fines too... are those unconstitutional as well?