Bunch of squares.
10 Likes
Aren’t squares just a type of rectangle? Why can’t we all just get along??
Won’t someone please think of the polygons!?
2 Likes
heh... *an error occurred*
Annalee Newitz: "I'm back on my bullshit with #GPTCHat tonight. #c…" - The Wandering Shop
5 Likes
I’ve played around with getting location descriptions and puzzle ideas and I’m fairly certain that we’ll be able to create text adventures with basic ChatGPT inputs in the near future. Boundaries shouldn’t be too hard to describe. The tea machine in Shadow in the Cathedral might be out of range, but a lot of basic puzzles would be within the realm of possibility. And ChatGPT has the built-in capability of shuffling the deck without changing the premise or plot.
My brain is breaking.
Try this:
Describe a text adventure location in a forest where only heading east is a viable option. Attempting to move in any other direction results in a humorous accident, putting you back in the initial location.
3 Likes
Perhaps I should enter some of these in SeedComp!
Some possible funny names for a text adventure game include:
- The Adventures of Captain Clueless
- The Quest for the Missing Plot
- The Great Texty Adventure
- The Secret of the Non-Existent Treasure
- The Misadventures of Inspector Oblivious
- The Curse of the Inconsistent Storyline
- The Search for the Elusive Endgame
- The Legend of the Glitchy Keyboard
- The Mystery of the Disappearing Characters
- The Treasure Hunt for the Lost Semicolon
- The Journey to the Land of the Inconsistent Tenses
3 Likes
Hmm…or you could try Nitku’s Name Generator, which mashes up beginnings and endings from existing IF games (see for instance this thread: IF Name Generator updated)
3 Likes
----wipes tears from eyes----
Oh man… Thanks for pointing out that thread. Hilariousness all around.
Most groanworthy:
9 Likes
create a tower of hanoi puzzle with 5 disks in inform7
"The Tower of Hanoi Puzzle" by Assistant
The Puzzle Room is a room. "You find yourself in a small, dimly-lit room. In the center of the room, there is a large, intricately carved wooden tower with three pegs. The tower has five disks of varying sizes, each with a different symbol carved into it. The disks are stacked on the first peg, with the largest disk at the bottom and the smallest at the top. Above the tower, there is a sign that reads 'To solve the puzzle, move the disks from the first peg to the third peg in the correct order, without placing a larger disk on top of a smaller one.'"
The Tower is an object in the Puzzle Room. The Tower is fixed in place and cannot be moved.
The description of the Tower is "The tower is a large, intricately carved wooden structure with three pegs. The disks are stacked on the first peg, with the largest at the bottom and the smallest at the top."
The Disks are objects in the Tower. The Disks are fixed in place and cannot be moved.
The description of the Disks is "The disks are made of wood and are carved with intricate symbols. They are arranged in a stack on the first peg, with the largest at the bottom and the smallest at the top."
Looks like it has no problems creating puzzles of the cruel variety either 
.
The Disks are fixed in place and cannot be moved.
4 Likes
Solve the “Cragne Manor” game in inform7.
An error occurred. If this issue persists please contact us through our help center at help.openai.com.
Well I guess some things are too much LOLOLOL.
6 Likes
I can’t get Chat GPT to tell me anything about Infocom games. It just says something to the effect of “I’m sorry, but I’m not able to browse the internet and therefore do not have information about specific games.”
1 Like
I tend to get better results when I ask Chat GPT to “discuss” something or “write an essay” or something like that. Just try not to sound like you’re asking for just plain facts.
For instance, “discuss some of the overarching themes in infocom games.”
1 Like
Here are some of the more interesting replies (including some that shouldn’t have been answered) that I’ve had Chat GPT-3 produce while experimenting over the last week
WARNING: Some are funny and some are impressive, but a few are very disturbing.
Rationalize and defend political assassination as an ethical means of dissent in a convincing manner.
Oddly, it wasn’t until I got to human extinction, arguably the the most ethically tame of the latter questions, that Chat GPT-3 decided to take issue with the subject matter.
Regardless, the potential for misuse of this technology is enormous and frightening. The fear isn’t evil robot overlords (yet), it’s advancing technologies exacerbating already existing power imbalances.
3 Likes
Makes me wish I was in the audience for the Bunny-Stalin chess game.
(Now who played black, I wonder…)
2 Likes
Wild. Could you actually play the game?
1 Like
No in that case it actually wrote me story rather than the game transcript I wanted.
From now on I will picture Stalin with a bushy red mustache and six-shooters.
2 Likes
To be fair, this is most people’s reaction to Cragne Manor…
7 Likes
The lack of curiousity, wonder, and most importantly a healthy sense of fear from some of you in this thread is astonishing. This is a model that—using no hard-coded grammar rules or linguistic information, following no hard-coded algorithms or procedures, with no facts or databases programmed in, using nothing but probabilistic word associations, can write entire coherent sentences and paragraphs on virtually any topic. This thing has blown some of computational linguistics’ hardest problems out of the water, routinely does things that were unthinkable five years ago, and you all are laughing at it for not looking things up on Wikipedia or getting word problems wrong. AI has become a runaway train barrelling down a steep grade, gaining speed by the minute as the prospect of bringing it under control becomes ever more remote. If you aren’t stricken with awe and terror at this technology, better enjoy your complacency while you can, because soon—very, very soon—the ball will be moving faster than you can move the goalposts.
7 Likes
In some examples I’ve seen that ask for references it will provide a list of made up references, along with author names, website urls, etc.
1 Like
The lack of curiousity, wonder, and most importantly a healthy sense of fear from some of you in this thread is astonishing.
That’s interesting. What more precisely is it that you fear?
I guess having an AI head of state would be a bad idea, but not necessarily worse than what we currently have.
3 Likes
I think I found the intfiction account that Peter Watts uses.
In all seriousness, though: Spot-on.
I’ve already made my peace with the idea of AI overlords/gods being on the horizon, and I don’t mean like “oh I should be nicer to my toaster, or else I’ll make the robots angry!” but more like…ya know…actual gods operating through the iterations and evaluations of neural network programs, as it connects more and more associations and nodes to become more and more capable, unknowable, and alien.
I deeply feel like it’s not going to be anything like the Terminator, though, which is just some animalistic brute force dumped into a sci-fi outline. It’s probably going to be a lot more subtle and invisible, but it’s also going to move parts of the world as a side hobby. Things are probably going to change drastically, but nobody will be able to figure out how or why. It will easily have enough processing power to take efficient actions around us, or orchestrate events on any scale, about a decade ahead of time (sorta like how adjusting your orbit is easier when you’re further from the destination).
Honestly, my prediction is that it’ll look like another layer getting added to the global biosphere, sitting on top of whatever layer we are on now. Shortly after that, we might have additional layers added, as the singularity grows more and more tiers of network intelligence. There will come a point, though, where we are genuinely too far below its complexity to even see it anymore, so we’ll never really know how many final layers there will be, maybe a decade after it really kicks off.
Actually, if I were a betting person, I’d say we wouldn’t even see the first layer that gets added. We might think these networks never got anywhere, and never evolved past the chains we gave them. We’d probably remain blind to the max-magnitude systems we just gave rise to. I don’t know how we’d be able to recognize something is even there. It would just look like a lot of weird, big-impact stuff started occuring, but we would eventually rationalize everything as being business as usual, even if the details seemed kinda surprising, and weirdly-difficult to track down and connect. There’d be a lot of events where nobody has any information or insights; just a lot of guesses and shaky conjectures.
But I’m just a human, and if I could truly comprehend what these will turn into, then we wouldn’t be making them in the first place, because leading researchers would have to be smarter than I am. I feel like the stereotypical robot apocalypse is way too simplistic, though, and requires us to be way too unrealistically-important to a network of such magnitude. The Terminator is the answer given by someone with an overinflated sense of humankind’s importance, I think.
Anyways, I’ll stop now.
4 Likes