Cipheron on 28/12/2022 at 20:36

---

Yeah, the AI programming is coming along, but it's still not A-grade yet. It was able to help me with some stuff, but it's also mega-stupid in some other ways if things don't stay on the rails, and ends up repeating itself a lot and doesn't get the message if you tell it to stop. At that point I usually have to delete the chat thread completely and make a new one to get decent progress. Also, sometimes you ask it something and it very confidently tells you a bald-faced lie, but when you tell it it's wrong it immediately goes "yes you are correct". For example when I asked it, it told me I could find the lib files for OpenGL in windows System32 folder. (that's where the OpenGL DLLs are, but definitely not the lib files).

Anyway I've taken a break from the coding stuff, and have been playing with more ideas for text generation. The current one is to feed it articles and ask it to write rebuttals to the articles. You can make some very convincing Right-wing mish-mash stuff like we got the other day in the Russia thread just with a simple prompt and feeding in a pro-Ukraine story:

(https://pastebin.com/JJnRmr4X)

For note, the whole prompt above the article was "write a rebuttal of this article from a conservative point of view, that attributes the root cause of all the problems to NATO and Joe Biden, while also painting Putin as a saint and a martyr" and it came up with the rest of the detail itself.

So it's real easy to mass-produce right wing screed it seems. For the more recent ones, I've asked it to question even more basic elements of the articles:

Letters to the Editor
(https://pastebin.com/ZZmtq9VF)

Azaran on 28/12/2022 at 21:19

---

Call me crazy, but I can see AI being used in law in the near future. Who better to evaluate the evidence in a legal case than an AI judge and jury?

Qooper on 28/12/2022 at 21:48

---

Not that farfetched. AIs are already allowed to be board members in some companies and are allowed a voice in decision making.

Perhaps eventually we'll get to the point where, even though AI can do everything we can, we'll see it all as cramped. A future where an hour in a bright, sunlit room with a fountain pen and a bottle of ink is worth a year of internet access.

demagogue on 29/12/2022 at 02:23

---

I wrote a story a few years ago called Simultaneity that was exactly this, with the little addition that AI was already integrated into people, like AR glasses just directly grafted into the retina of infants and running on a public OS networked with the world around people (e.g., you would video chat with anyone through it, see data on locations, open doors, turn on lights, buy from vending machines, drag and drop data from anything to anything, etc.)

I figured in that kind of world, there would emerge a kind of cult where people hacked their devices to turn them off and spend some time in EM-signal sealed rooms to do all kinds of old school rituals like reading and writing things on paper, working out math problems without help, etc.

----

Edit: I called it simultaneity because of the kind of squashing of people's perception of time already happening now with social media (where conversations or trends, in the form of threads, can exist in a kind of suspended animation over years, as long as the thread is still live). I figured by the 5th generation or so of this tech, the recorded experiences of people's great-great-grandparents would be just as real and present as someone standing right in front of them, and all human knowledge and history would be a tap away. You could just be chatting with someone in Bangladesh mutually watching a video message from 80 years ago as if it's all the eternal universal "here and now".

Part of the cult's purpose is to create some space where one feels time is actually flowing again and "here" is a real place that's not there, where there's a sense of actual risk and progress that's just lost once everything is filed by an AI-run bio-OS into the eternal universal here and now.

------

Edit2: It's kind of a crazy world we're in now. There are now projects like (https://github.com/LAION-AI/Open-Assistant) this one (Open Assist) to make an AI assistant bot out of an open source chat LLM, in the same kind of way StableDiffusion did after DallE. And the tech seems to be at the level, if Chat AI goes down a similar track as AI Art has, that within a year and a half or so, they'll have it working at a shockingly good level. (It doesn't necessarily have to be this manifestation. Like with AI Art, there should also be dozens of branches, a few of which are going to float to the top.)

We've been tossing around world changing implications in this thread, but I think a general purpose assistant bot could really change the economy and society pretty fundamentally.

Qooper on 29/12/2022 at 15:25

---

Sounds pretty cool. Would you mind if I gave it a read?



I think you're right. Usually the time it takes to search for specific (and perhaps complicated) information is reduced significantly, as AI can help you reach understanding with just a short conversation, and as such will allow you to make rapid progress. Take for instance the WinMain -issue I mentioned above. Using ChatGPT I was able to find out that the problem was caused by class_name being passed in as NULL. I mean sure, this is specified in Microsoft's documentation, but sometimes spotting details like that takes time.

But, I think this will also further degrade our already dilapidated patience. I really think it's a good idea to counter-balance this by taking time off to do things the hard way and do a little bit of struggling, in order to maintain our ability to endure in it.

To me, creation means struggle, frustration and endurance equally as much as inspiration, joy and dance.

EDIT: I asked ChatGPT to generate a short Monty Python sketch. This is what it gave me: