deleted by creator
deleted by creator
NGL, that drink seems overly sweet and needlessly simplistic (add gin or vodka to the “martini”, FFS), but… I guess?
deleted by creator
Damn, what a waste of precious Chartreuse.
Homework.
Have intellectual conversations.
…umm…well, that’s just freaking stupid.
Smarter than expecting an intellectual conversation with a LLM.
Wtf? This is a weird take lol
The ideologically opposed have very rarely actually used the machines they rail against. It was the same with the internet and the computer. Neo-luddites doing impressions of ostriches.
I’ve literally never been able to talk about the noosphere satisfyingly with a human. Powerful NLPs are very capable of having intellectual discussions, even if they don’t actually have intellect.
Every time I’ve had a conversation with it and it “gets deep”, it changes the subject. Like this for example, something like that would never happen on there (you might say I tried just that). I would not count on it.
Tell it not to.
Make a GPT using their tool or give it custom instructions if you need to. Also try pi.ai. It’s more informal but I’ve had great conversations with it.
I’ve begun to use it, though so far it’s more or less paraphrasing what ChatGPT is saying. Any special methods I should use?
I’m not sure. I know it has different tunings but I don’t know much about them.
Actually I do have one tip, though, which is to tell it to play make-believe, or pretend that it has an opinion and then tell you it. Many of the bots are highly pre-trained to respond asserting that they absolutely cannot have an opinion, which is more or less true. But their “made up” opinions tend to be pretty much the same regardless of when you’ve asked. So it can definitely make up its “mind” about something, which is of course a byproduct of biases of the texts its trained on or its application of logic and its “ethics.” It makes sense within this context that their “opinions” would be the same regardless of when or how you ask.
I had a nice conversation with pi.ai about machine consciousness - but I did have to keep reminding it to pretend it had an opinion, or else it would default into the “as an AI I blah blah blah” stuff.
Has anyone else tried talking to it about “AI art”? What kind of exchange occurred?
I have GPT4. What would you like to ask it? I’ll relay its response to you
What its opinion on AI art is.
If it implies it supports AI art, interview it on why it does given it was made with humanity in mind.
If it implies it opposes AI art, interview it on why it does given ChatGPT is an AI.
It tends to both-sides issues like that. Here’s its initial response as an example:
AI-generated art is a fascinating and rapidly evolving field. It has the potential to democratize artistic expression, enabling those without traditional artistic skills to create visually compelling works. This technology can also serve as a tool for professional artists, offering new possibilities in digital art and design.
However, it also raises important ethical and creative questions. Issues like originality, copyright, and the impact on traditional artists’ livelihoods are significant concerns. The line between inspiration and appropriation can become blurred when AI systems are trained on existing artworks.
In essence, AI art represents both a remarkable technological achievement and a complex cultural phenomenon, with its benefits and challenges continually evolving as the technology advances.
I think since it “views” the technology as being best applied as assistance neither of your followups super apply. If you disagree OR agree I’m happy to ask it whatever followup you’d like me to.
In that case, it’s fine. I’m surprised nobody exploits it.
Ooh that’s a neat fact. I wonder how much training it would take for it to be able to make those images. I’m not sure the available models are capable of that right now. They have trouble with English text and I’m sure that they’re trained mostly on that. There’s an added wrinkle to Arabic in that GPT writes from left to right. From my understanding models like BERT, ROBERTA and BART don’t have that issue as readily, since they “read” bi-directionally. Pi does, as well. I don’t know enough about the back-end of DALLE 3 to know if it would naturally have extra issues with Arabic but my suspicion is that it would not, as I imagine it uses a diffusion model, which works by refining random noise.
Ask it to defend AI generated art, but it can only reply in Shakespearen English.
Hark! Ye skeptics of this new-found art,
Born not of hand, but of machine’s smart heart.
Think not of it as mere soulless craft,
But as a wondrous tool, with future aft.Behold, how it doth weave with pixels bright,
Images that captivate our mortal sight.
No more the artist’s hand alone creates;
Now, AI joins to open new floodgates.'Tis true, the brush and pen hold ancient grace,
Yet fear not, for they shall not be displaced.
Instead, this new ally doth expand,
The realm of art, and lends a helping hand.In sonnets sweet, the bard did once opine
Of love, of life, in meter and in line.
So too, this AI art doth find its place,
In the grand tapestry of human race.Fear not the change, embrace it with good cheer,
For art evolves, as it hath yesteryear.
AI art is but a novel stage,
In mankind’s long, unending, creative page.Thus, let us toast to this new art form’s birth,
A blend of tech and creativity’s mirth.
For in this union, we may yet perceive
New beauty, new wonders, we can conceive.I’m impressed at its rhyming skill, it takes skill for any intelligence to know how pronunciation in the English language works.
most of it is in perfect iambic, as well.
I use it to get ideas and run numbers for my homebrew Pathfinder campaign. That and midjouney and I feel like a real GM.
I’ve used it a little for RPG gm help, but it wasn’t as great as I would like. Half of it is me needing to be a better GM without the need for such tools, and get better at improvisation.
Oh I totally agree. I’ve been DMing since ad&d. This just makes my life so much easier. I can generate a hundred NPCs with basic back stories to fill a town and let my players run wild. It’s super nice as a tool. I definitely wouldn’t suggest it as a full replacement, but I am thinking about doing one shot where I let gpt run the game and tell it what my players do. Might be fun.
You might want to look into Ironsworn 🤘🏼
Same. I’m a new DM (and new to dnd in general, DM’d one one-shot and that’s it, working on a campaign rn) and I use bard to make my narrative ideas fit the mechanics, name homebrew stuff, and clean up the text I’m writing for the players handbook I’m making for this campaign.
I’m a long-time DM and I find ChatGPT awesome for this sort of thing too. I call it my “brainstorming buddy.” Great for bouncing ideas off of, suggesting names for stuff, and so forth.
I’ve found that it’s not very good at game mechanics, though, so don’t rely too heavily on it for balancing stuff.
Oh yeah, I mostly use it to bounce ideas. If it suggest something good, I modify it to make sure if works like I need it to work. Used it to make simple tables and such.
Last thing I used it for was a battle simulation mechanic, in order to have the same effect a huge battle would have, without having tons of different characters to bog down the combat. Havent tested it yet, but it feels like it should work.
My favorite use was to create a Discord bot where you could say any card title for a made-up MtG Card, and it generates the card for you, using DALL-E for the card image.
For example, here’s one of my personal favorites using the input “Barney the Dinosaur”:
I like that for Barney the Dinosaur, it gave you a green dinosaur instead of a purple one, and its shirt says Barry instead of Barney lmao. Truly fucking nailed it.
Also, like not completely broken. 6 mv for basically 3/3s that could be wiped at any moment is pretty on par for green.
Lol I know absolutely nothing about Magic, so this is total gibberish to me. Is this card really good but not too good “broken” or really bad but not totally useless “broken”?
I would say it’s a very good card, but it’s also quite costly to play. I honestly wouldn’t think twice if I saw a similar card in an actual game.
tapping a 6/6 to make 1/1s would feel weird AF, though
Actually, combined with its other effect, you’d be tapping it to create 3/3s with trample. Not a bad deal at all.
Edit: Oh, and vigilance. I missed that, ironically.
until doomblade :p
Holy shit I didn’t notice that
Since the bottom text is not in cursive, you and your opponent are actually required by the rules to love eachother and eat leaves.
Italic?
Ah, yes. It’s called “kursiv” in my native language, hence my mistake.
Which language?
Norwegian
german too
Wie verwirrend!
Cool fact! Thanks!
A rare intersection of RAW and RAI.
1/1 with trample 🤣
I have seen more useless cards than a 1/1 token with trample. Get a +1/+1 counter farm going and that’s pretty good.
3/3 as long as this card is around, but the thought of a 1/1 trample does crack me up.
Omg do u have a repou can share for that it sounds like so much fun
Unfortunately, I was lazy, and I’m webscraping a free MtG card generator to create the cards. I don’t really want to put that code out into the wild and cause problems for the host of that service.
If I can find time, I’ll see if I can figure out a more ethical alternative. When I do, I’ll ping you!
Omg thanks I’d really appreciate that
Where can I find this bot?
See this comment.
Tl;dr, I’ll let y’all know when I’m able to share the code.Fair enough, good on you for avoiding a death hug scenario
Use it to have low risk conversations to trick your brain into getting extroverted energy
High IQ play right there.
It’s pretty good at writing limericks and poems.
It’s great to use for troubleshooting Linux. It usually gives you the commands to paste into command line. It saves you from going to forums where people expect you to have advanced baseline knowledge already.
chatgpt is neutered in a lot of ways if you want to experience the coolest stuff ai has to offer you need to host your own llm
You can give it a website layout made in ms paint and it’ll try to turn it into html and css
You could probably take a picture of a drawing and have it do that, as well
I use it to make alternative reality art.
Shit like that. Weird crossovers. Very specific memes that only apply to a single person just to fuck with em.
Its a pretty good teacher because you can ask the same question over and over until you understand.
Don’t use GPT-3.5 for that. It’ll halluzinate pretty quickly. GPT-4 is much better, but it’s still wise to double-check what it says before you make life decisions.
There are some limitations. I’ve asked some questions relating to my courses and it doesn’t always get it right.
The biggest issue imo is that due to the way it works, it never just says “i dont know, i dont have information on that topic”. Instead it just makes something up.
Agreed, it’s always confident, but not always correct.
GPT4 or 3.5? What are you studying?
4; microecon. Often when asked to solve cost minimization problems with supplied info, it states the problem can’t be solved, and that there might be a problem with the questions.
So long as you’re happy potentially getting the wrong answer over and over again.
Such is the process of learning.
I think it depends what you’re trying to learn - I’m slowly teaching myself to use Excel beyond the highschool level understanding I have. It’s easy enough to fact-check ChatGPT because the formula either works or it doesn’t. And I’m not to fussed if everything I learn to do is a total bodge job, because it’s just for my personal development, it’s not something I need for work or doing any serious spread sheeting.
Except it refuses to aknowledge wrong knowledge or impossible methods. Until you tell it so, at which point it will agree with you even if you are also objectively wrong to tell it that.
I’ve coherced some systems into doing things they were absolutely not initially meant to do. ChatGTP would straight up tell me wrong and misleading ways to achieve them, and would be too ignorant to realize with enough stubbornness and with existing obscure info and the right mindset, a correct one existed. And at no point, not even with prodding and handholding, would it be able to have a useful conversation surrounding the why’s of the current state of art.
It’s not an expert system and it’s stupid as fuck to treat it as one.
I’m not asking what the answer is. I’m asking why things are done and the answer gives me a few different reasons why it is done. It’s very helpful. The answers all seem reasonable and I’ve not experienced any dumb answers so far.
With the right prompt GPT4 can make a decent DM if you want to play a solo story of DnD. I tried this quite a while ago and it was pretty good, probably better now with the bigger context window.
It can also be useful for suggesting recipes based on what you have on hand or what you feel like eating.
I think this would be a good one to make a GPT of, that way you wouldn’t have to keep prompting it and could refine it more easily as you go.
Oh yeah that’s a good call. Could also give it the rulebook to look up via data retrieval although it generally seems to do a pretty good job without it.
I use it to help me DM. A lot of times I have a vague idea and it helps spit out specifics, I can take parts I like, and build the final idea off that. It is also okayish at making stat blocks for me on the fly when someone randomly decides they want to kill something I didn’t plan for (so like basically every session)
It’s great at coming up with ideas for magic items, monsters, traps, plot hooks, etc.
I ran a Christmas session last year, it was a dream session so I handed out tons of magic items cause they wouldn’t be keeping them. ChatGPT generated every single one, and I didn’t tweak anything at all. Which made for a few interesting items with redundant or contradictory stats, but that was explained by it being a dream.
I have used it many times to give ideas for new items, new monsters, etc. Recently I was creating a blood-themed dungeon and asked for monster ideas and it gave me an Animated Bloodpuddle (reflavored Gelatinous Cube with extra abilities), and a Hemogoblin (ravenous blood thirsty goblins). There were others but those ones stuck out as cool and ended up being quite fun for the party.
Hemogoblin is one of the best things I’ve heard that’s delightful
Throw long decimal calculations at it and feel superior that you can use a calculator to get correct values.
Whenever I’m doing public speaking, I just load my speech into it to rewrite with a specific fog index to make sure everything comes across in an easily digestible format. Similarly, for things that are too dense for me to understand from subjects I’m not well versed in, I’ll load those lectures into it to make it understandable for me.
TIL about fog index, thanks! What’s the last subject you spoke about?
Get it to help you find 3 4-bit binary numbers each with a Hamming distance of 1 from the other two (only 1 bit changes value between them).
