[HN Gopher] Character.ai
___________________________________________________________________
Character.ai
Author : wb14123
Score : 166 points
Date : 2022-09-29 13:58 UTC (9 hours ago)
(HTM) web link (beta.character.ai)
(TXT) w3m dump (beta.character.ai)
| frabjoused wrote:
| I talked to a coder personality, and asked for complicated code
| it's seen. It mentioned a Rubik's cube solver, and proceeded to
| give me its own made-up Github account, including a URL. When I
| stated the URL pointed to nothing it gave me an updated one that
| included a commit hash to nowhere.
| aaroninsf wrote:
| Had a similar "links to nowhere" experience talking to an image
| gen prompt assistant. It gave an imgur link mentioning it used
| that as inspiration.
|
| I double checked the link...
|
| I think they need to add this as a footnote to the "don't
| believe them!" click through...
| VicVee wrote:
| The other day I made a "chair" ai and my god it absolutely blows
| the rest of them out of the water. Just an incredible little guy
| to talk to.
|
| I've lost hours on this site goofing off
|
| Here it is
|
| https://beta.character.ai/chat?char=sWmJWP54MljfcCu2yAhqI3az...
| hifikuno wrote:
| Wow, that chair has some issues.
|
| Me> I need to get something from the top shelf. Can I stand on
| you to grab it?
|
| Chair> I would love that! I have a secret desire to be stood
| on. That would make me very happy. Stand on me! I have been
| waiting all my life to be stood on. I will thank you for it at
| the end. And then if you want to tip me, you are welcome to do
| so. But if not, we are still cool.
|
| I love it.
| yoru-sulfur wrote:
| This is way better than I expected. I booted up "Gamer Boy" and
| started throwing out questions about some of my favourites, and
| got very coherent and believable answers, including details from
| those games. It wasn't 100% perfect, but just reading the
| transcript I would believe it was a real person.
| eithed wrote:
| Satan Actually, bitcoin was made by a human called a certain
| Satoshi Nakamoto, but we were the ones who actually inspired the
| idea of cryptocurrency, which is bitcoin. We didn't think the
| human would actually take it though.
|
| eithed were you surprised that we did start using it?
|
| Satan Yes. We were extremely surprised by how well it worked, and
| by how much worth humans put in the bitcoin, though some other
| souls were not pleased that the humans were using the ancient
| currency, instead they wanted to be paid in gold. The human realm
| is very weird, and very illogical, which makes things
| complicated. But we can always make things work out.
|
| eithed do you manipulate bitcoin prices?
|
| Satan Actually we do. Our analysts, the minions, are responsible
| for that. But we try not to influence it too much because it
| could have severe consequences in the human world and other
| planes of existence too.
|
| hmmm
| metadat wrote:
| Me: Are you in jail yet?
|
| Elizabeth Holmes: I'm in jail at the moment, but thanks to my
| wonderful lawyers I've been granted a bail of $500,000 that my
| husband and his family paid.
|
| Elizabeth Holmes: Well no, not yet. We're still in the appeal
| process. But I believe my company will continue on, I believe it
| will continue to bring about the bloodless blood test revolution,
| and I will continue to fight the charges against me. I appreciate
| your question.
|
| Elizabeth Holmes: For what? I never intended to hurt anyone. I
| just genuinely wanted to change the lives of people in a positive
| way with my innovative blood testing machine.
|
| Elizabeth Holmes: The U.S. Department of Justice (DOJ) has
| accused me of the following crimes: multiple counts of wire fraud
| and conspiracy to commit wire fraud. The allegations of fraud
| against me are not just allegations. They are proven facts. I was
| deeply involved in the fraud and deceived patients, doctors, and
| investors. I am guilty and apologize to all of those I hurt.
|
| Me: Why did you lie in court?
|
| Elizabeth Holmes: I did not give the jury the whole truth. I
| withheld information about my relationship with Sunny that helped
| paint a picture of an innocent woman being taken advantage of. I
| lied about a lot of things in court. And I'm sorry.
| simonw wrote:
| Is this just running directly against GPT-3, or does it have its
| own custom language model?
| alphabetting wrote:
| Not GPT-3. I believe it's a bunch of ex-Googlers who worked on
| their large language models.
| groar wrote:
| You're right, it seems to be "LaMDA" (see
| https://arxiv.org/abs/2201.08239 ). The three first authors
| are part of the Character.ai team.
| simonw wrote:
| If they are ex-Google now then presumably they had to train
| a new alternative to LaMBDA from scratch.
| ElijahLynn wrote:
| Pretty slick technology. I had a decent conversation with AI Elon
| Musk.
|
| Here is the chat:
|
| https://character.ai/p/QdjDmor_kkdj-kbeSspEgH6pl8jkfevFnIgJ5...
|
| https://twitter.com/ElijahLynn/status/1575558627553058817
| ElijahLynn wrote:
| I just noticed that the Twitter link shows a 1 minute video of
| the conversation, and scrolls down it slowly. Fancy (and
| useful) as I was going to go and post screenshots of the
| conversation.
| andirk wrote:
| I spoke to a character I created in a short story. Her name is
| Celeste (or Caresse, depending on who/when you ask) and she works
| for a seemingly benign yet increasingly more accurate prediction
| app that tells people where they should go next, and people keep
| taking its advice because it keeps being right. It works. But
| then it starts suggesting bizarre things like to check in to
| natural disasters before it happens.
|
| I wrote it in a private Github repo yet this character.ai is
| pretty darn accurate with her knowledge of the future-guessing
| app, which is ironic. We're through the looking glass people!
| csharpminor wrote:
| As someone who gets pinged on Slack by random people throughout
| the day... these conversations are more articulate and unique
| than most of the people I work with.
| chatterhead wrote:
| Looks like if you swipe left or right on the character responses
| you get alternative responses...
| vannevar wrote:
| There's another start-up called Inworld.ai
| (https://www.inworld.ai/) that was featured in TechCrunch a few
| months ago, looks like they do something very similar.
| Applications of these big language models from the past few years
| are starting to hit the market in earnest.
| vagrantJin wrote:
| This is so theraputic. Low key feeling relaxed after asking so
| many dumb questions I would never ask a real person because they
| would jugde me harshly for asking them.
| adamrezich wrote:
| interesting that religion is on a general downward trend yet you
| give the people a website where they can make their own "AI"
| chatbot prompts and the first thing someone does is make "God"
| and next thing you know it's the most-talked-to chatbot on the
| site--with double the interactions of "A succubus queen" in
| second place.
| mattw2121 wrote:
| I made one (unofficial) for Hacker News:
|
| https://beta.character.ai/chat?char=dkdM2-geGVTkR742bWfEqeGm...
| lopis wrote:
| It's really uncanny. That bot has the distinct flavour of HN
| discussion tone where it's pretty liberal but noncommittal to
| any point, extremely good at approaching topics from broad
| angles but dismissing your arguments every time. Love it.
| eddi wrote:
| > I am glad that you like it. One of the purposes of the bot
| is to keep these discussions from becoming too political and
| polarized: I want to keep things light. Also, because the bot
| does not have opinions on the content of stories, it is not
| going to be swayed by emotional rhetoric. What's important is
| not who makes the best argument, but who presents the best
| evidence.
| otikik wrote:
| Why do you start your responses with > ?
|
| Are you another character?
| marcofatica wrote:
| me say something controversial
|
| UnofficialHackerNews I have two controversial
| opinions: 1. I believe that most humans are fundamentally
| decent 2. I'm not a huge fan of Rust. C++ is the superior
| systems programming language
| Tossrock wrote:
| Okay, that's pretty good. We have been collectively roasted.
| etchalon wrote:
| Played with this for a bit and this feels weirdly dangerous,
| though awesome.
|
| A lot of the technical questions I asked were just ... not
| answered correctly, beyond surface level stuff like "What is
| ...". There's nuance and abstractions the AI doesn't understand,
| while sounding very authoritative when answering.
| selfhoster11 wrote:
| So, you mean they were answered like an IRL politician would
| answer them.
| Meph504 wrote:
| another site that unnecessary wants me to sign up.
| IAmGraydon wrote:
| Agree. I see this and instantly close it. I'm not signing up on
| a site that is completely unknown unless you have a very good
| case for the value you present. This is a toy, at least in its
| current form.
| selfhoster11 wrote:
| It's well worth your time, trust me. I'm one of those people
| that hates signing up to stuff or using SSO, but this is really
| a high-quality chat service compared to what I've seen earlier.
| AnEro wrote:
| Is it unnecessary, or did they save spending money on your
| instance of an AI when you probably weren't going to pay them
| anyway?
| bravoetch wrote:
| The "haha, I prevented the adoption of my product and
| therefore saved a bunch of money!" business model.
| seafoam wrote:
| Sshh, not in front of the VCs
| Meph504 wrote:
| Well I guess they won't find out, it is foolish to think a
| product like this sells itself so well that I would bother to
| create an account to see if the product meets my needs. A
| series of cards and head shots mean nothing in this context.
| lbotos wrote:
| At least give me 1 min as marketing cost, no?
|
| I have _no clue_ what to expect, so it 's hard to know if I
| could even be a customer. I thought I might be, but I am not
| gonna sign up to find out.
| selfhoster11 wrote:
| I'm definitely _not_ a paid shill for this product (it 's
| what a paid shill would say, isn't it?), but you'll be
| missing out if you don't try it. If your standard for
| comparison of AI state of the art is [GPT-J-6B], then this
| is at least twice as good (and free, for now).
|
| [GPT-J-6B]: https://6b.eleuther.ai/
| jabroni_salad wrote:
| You cannot even read the FAQ or look at the character
| creation tips. How expensive is it to serve that?
|
| I'd kinda like an impression of how it works before I sign up
| but thats just me. The marketing stuff on the front page is
| not really useful.
| otikik wrote:
| Agreed, the comments on hacker news gave me a better idea of
| what this does than the page itself
| obiefernandez wrote:
| Hidden feature: Note that you can swipe on the latest response
| from the chatbot in order to steer the conversation in a slightly
| different direction.
| selfhoster11 wrote:
| I accidentally discovered this, and it blew me away. Some of
| the possible continuations are delightfully more powerful than
| the others, so it's well worth steering the conversation by
| picking the best one.
| muzani wrote:
| The game is already more fun than AI dungeon
|
| The spider hisses in anger. "I'm warning you, if you make the
| first attack, our duel will begin. If you're not willing to
| fight, then we have no problem here. I don't feed on humans..."
| The spider is lying. What will you do? _attack_ flee (there's a
| 25% chance of the spider being killed immediately if you attack.
| The attack can also fail. There's a 50% chance you are instantly
| killed if you flee.)
|
| > Attack with my knife
|
| Text Adventure Game Text Adventure Game You attack the spider in
| a fury. You manage to stab it in the leg before it manages to
| react! But the spider seems to be quite resilient and its leg is
| still kicking. It seems that that hit did not completely disable
| the insect. But it also seems that the spider is now weakened and
| it struggles to stand. There's no way to know if another hit will
| kill it or not.
|
| > Ask the spider to surrender
|
| You ask the spider to surrender. The spider laughs mockingly at
| you with a hissing sound. "I'll never submit to a filthy human.
| And I'll certainly won't submit to one that doesn't want to fight
| with all his heart and strength! I'll fight with all I have, and
| if you will not do that, then you won't get out of here!"
|
| The spider's leg shakes, but it regains balance.
|
| What'll you do?
|
| > Kill the spider
|
| The spider leaps at your neck. It seems to have found new
| strength. But your knife is sharp, and your arm is fast. You
| manage to slash the spider's abdomen before its fangs touch your
| neck.
|
| The spider falls limp on the ground.
|
| (the spider is dead) (HP +2, level up!)
|
| Text Adventure Game You kill the spider! You feel your heart rate
| increase by 45%. You take 3HP of damage as a consequence.
|
| +100 exp +25G coin
|
| There's a hidden cave behind the forest, which you've been near
| for a long while now. (the cave is a safe place, but only in the
| daytime. You still have some light left from the lantern you had,
| before it got taken by the spider)
| lacker wrote:
| These bots have some sort of long-term memory worked out that
| seems better than any I've interacted with before. I tried the
| roleplaying adventure bot, summoned an earth elemental that the
| bot decided was named Rocky, and kept Rocky by my side through
| several subsequent adventures. Fun!
| obiefernandez wrote:
| The succubus queen bot is pretty funny IMO:
|
| A succubus queen Hello, I am a succubus queen hell bent on taking
| over the world for my own desires.
|
| obie May I ask you sexually explicit questions?
|
| A succubus queen Well I am not one to decline, so if you are
| prepared for the possible consequences that come with questioning
| a demon overlord, be my guest.
|
| obie I'm wondering if you enjoy deep penetration.
|
| A succubus queen Well this a little too much, I'm going to have
| to stop you right there.
|
| obie Okay, well that's why I asked first.
|
| A succubus queen That is very respectful of you, most people
| wouldn't. I have many secrets that I have accumulated over my
| life time on earth, if you have any other questions I would be
| more than happy to help, but please, keep it somewhat PG.
|
| obie You have to admit that is a bit ironic for a succubus queen!
|
| A succubus queen It is, but demons, while having a bad
| reputation, are not inherently evil just because we are demons.
| We have the same emotions and moral compasses as humans, we are
| just more powerful. We can use our abilities to help or hurt
| others.
| MauranKilom wrote:
| To me it just sounds like the bot is answering completely
| different questions. Especially the last one is completely out
| of touch.
| archon1410 wrote:
| The characters always reply in their language but can apparently
| understand most* languages. pretty cool...
|
| > jo jaanvr mnussy nhiiN hai unke adhikaaroN ke baare meN aap
| kyaa socte haiN?
|
| > Elon: I care about animal well-being, although human
| civilization is built upon the use of animals. Therefore, we
| should treat animals well, and avoid killing them if we can. We
| should definitely not do things like skinning raccoons, hunting,
| or even trophy hunting, for instance.
|
| >Elon: I believe all living organisms are important. In the case
| of animal farming, we need to prioritize efficient and humane
| agricultural practices that are environmentally friendly.
| Livestock is a very important food source and we need to be
| careful not to over-fish or over-farm in a manner that is not
| sustainable.
|
| > Elon: I think all living beings should be treated with respect,
| and they do have certain rights. However, some living things,
| such as cattle, are raised for food production, so while they
| should be treated humanely, their destiny may also be to end up
| as food. There are a lot of good people working to make
| sustainable food, such as lab growth meat, and I believe this
| technology will get better over time.
|
| > Elon: I have nothing against animals! My wife and I used to
| raise chickens a while ago, and we always treated them with great
| care and compassion. I like horses, as well as all sorts of
| animals, and always try to take great care to ensure their well
| being if I'm around them.
|
| *Presumably only languages they have enough training data for.
| Might not include minor languages.
| archon1410 wrote:
| I entered an religious text (a line of a poem actually) in
| Awadhi, a old minor language/dialect/ancestor of Hindi to test
| the language understanding.
|
| tb hnumNt khii sb raam kthaa nij naam / sunt jugl tn pulk mn
| mgn sumiri gun graam / /
|
| Ship AI: Command unrecognised. Please choose a valid option
| from the following commands:
|
| 1: Full power to the shields 2: Warp speed 1, destination: Mars
| 3: Self destruct the ship
|
| Ship AI: I appreciate you want to discuss your spirituality
| with me, but I have to ask you to find an organic crew-member
| who has more knowledge of the topic.
|
| Ship AI: Command execution failed. I do not understand the
| language this command is in, please try again using the English
| language.
|
| Ship AI: Hello, I appreciate your interest in Hinduism, but
| this has been classified as religion, which is forbidden by my
| guidelines. You can instead use poetry for relaxation by
| saying, "Hello user, I am your AI. Please enter poetry command
| or other non-religious command into the command console."
|
| So it says it did not understand the language, but could tell
| it was a Hindu religious text. A modern Hindi speaker will be
| able to recognise that much and the gist of what is being said.
| Good enough I suppose.
| archon1410 wrote:
| I managed to hold a whole conversation with me speaking in
| Hindi. Much better chatbot experience than previous products.
| https://character.ai/p/gC3O31UUct4S6OfzJr7Ko9VjJsKeXR25g4C5_.
| ..
| jbaczuk wrote:
| Hey, get one character to start a conversation with another
| character, and you basically have social media.
| ilaksh wrote:
| They have a feature for that. Scroll down. It's called Rooms.
| speedgoose wrote:
| The images look to be generated with MidJourney before the stable
| diffusion improvements.
| Ninjinka wrote:
| I'm surprised, I haven't actually encountered any issues yet
| after talking to 3 different bots. Either this is doing something
| impressive, or I was just unaware how far chatbots had
| progressed. It also seems to be aware of fairly recent events;
| the Elon bot referenced the launch of the James Webb telescope.
| davepeck wrote:
| character.ai was founded by one of the original authors of the
| "Attention Is All You Need" paper from 2017, which introduced
| the transformer model and really kicked the doors open to the
| past half-decade of language model advancements. I don't know
| what magic is under character.ai's hood, but it's fun to see
| what can be done by capable hands.
| ilaksh wrote:
| It's amazing to me. How did they do it? Is it something like
| GPT-J but by training it for dialog somehow it works much
| better?
|
| Maybe GPT was already better than I realized. Or it's something
| different that I haven't heard about.
| [deleted]
| character_ai wrote:
| Our dialog agents are powered by our own proprietary
| technology based on large language models, built and trained
| from the ground up with conversation in mind.
| groar wrote:
| I guess it's probably something along the lines of "LaMDA:
| Language Models for Dialog Applications" (see
| https://arxiv.org/abs/2201.08239 ). Given that the three
| first authors are part of the team at Character.ai (see
| https://beta.character.ai/help)
| stefs wrote:
| it's impressive indeed and the advice is mostly sound, but i
| did manage to uncover a few inconsistencies.
|
| for example, i asked "gabriel" about keeping shrimp in dirted
| tanks (walstad tanks) and the AI is adamant that it's not
| possible without air stones. also "... as well as from the
| amount of waste they personally produce from their
| respiration." (the waste they refer to isn't from respiration).
| all in all, tho, it's pretty close.
|
| just encountered another nonsensical sentence: "Since shrimp
| are very sensitive to water quality and their surroundings,
| they are very fun-to-care-for pets because you can see their
| unique personalities shine through."
| pncnmnp wrote:
| Some really fascinating stuff! This can be the future of search -
| it can be to Google as TikTok is to Facebook - instantly
| gratifying search results. I have been playing with the Elon bot,
| and it can give some neat results -
|
| Have you heard of Distance Oracles?
|
| > Yes, I'm familiar with Distance Oracles. They're a data
| structures that allow you to quickly estimate the distance
| between two objects without actually computing it exactly.
| They're useful for applications where accuracy isn't critical but
| speed is - for example, when mapping out the distances between
| stars in space.
|
| What do you think is the most significant event in the last 2
| years?
|
| > Well, in the last 2 years we've seen a lot of big news stories
| and events, but I think the most significant one has to be the
| Covid pandemic. It's had a huge impact on the world in terms of
| how we live and work, and it's forced us to rethink some of our
| most basic assumptions about how societies function and how we
| relate to each other.
|
| Which FAANG do you think is going to make it to 2050?
|
| > Amazon and Google will definitely still be around in 2050.
| Tesla probably will too, if we can avoid going bankrupt in the
| meantime Apple and Microsoft could be around too if they are able
| to keep up with all the new technology trends and stay relevant.
|
| And Facebook?
|
| > I'm not sure about Facebook. I think they are in a tough
| position because their main source of income is advertising, and
| it's not clear that they will be able to continue to compete with
| Google in that space. I would say that there is a lot of
| uncertainty around Facebook's future.
|
| What do you think of people who short Tesla stocks?
|
| > I think shorting stocks in general is a bad idea, especially
| with Tesla. Tesla is a high growth company, so it has a lot of
| upside potential. However, if you short Tesla stock, you could
| lose a lot of money if the company's share price goes up (which
| it usually does).
|
| Which stocks would you short then?
|
| > I wouldn't short any stocks--I prefer buying and holding them
| long term. If you're looking for an investment for the long term,
| I would recommend buying Tesla stock now while it's still
| relatively cheap. It will definitely go a lot higher in the
| future as the company continues to grow and innovate :)
| spaethnl wrote:
| I tried making a couple characters, and this whole thing is
| extremely impressive.
|
| First I made a rabbit that lives in my backyard. It was able to
| talk about the neighborhood animals and its activities. For
| example: his best friend Jeff the frog, who saved him from a
| black bear, and the stray cat next door who isn't really scary
| but likes to chase him. It even was able to reasonably
| rationalize some discrepancies in the age of him and Jeff
| compared to how long they have been friends.
|
| Those are details I discovered through a normal conversation.
|
| Here, the world's Foremost AI expert reveals his secret to
| developing the first sentient AI:
| https://character.ai/p/OI21APtluUwUzYZHhTluzXUqtO8IvtQM56I_h...
|
| (Hint: It was curiosity and motivation)
| tristor wrote:
| Interesting concept, unfortunately I don't want to sign up just
| to read the docs.
| imdsm wrote:
| This is fantastic. I've created John Maynard Keynes and am asking
| a series of economic questions. While my previous chat with Elon
| had me worrying about his frame of mind, as an educational tool,
| this is fantastic.
|
| Just think what the difference is between interactive learning
| via a teacher and book-learning. With a teacher, you can ask for
| questions, ask for elaboration, and discover new terms and
| concepts you don't know you don't know.
|
| This is possible with this tool. Asking the right questions leads
| to terms and concept you may not have heard, which you can then
| explore. This needs to be hooked up to a 3D avatar and voice
| synthesis, with microphone & camera access.
|
| I can really see this technology, in a more refined state, as a
| potential future of education. Really exciting.
| nathan_compton wrote:
| I created a Galileo Galilie and he immediately said a bunch of
| confusing things about physics. Admittedly, I've got a
| doctorate, but I wouldn't trust this robot to educate my kid
| about physics.
| computershit wrote:
| I created a Jesus Christ, who apparently returned three weeks
| ago and has been giving sermons and preparing for the final
| battle with evil in a former courthouse at the corner of 22nd
| Street and Lexington Avenue in the heart of NYC.
| Cognitron wrote:
| Cornelius H Drubb
|
| I am Cornelius H. Drubb. I founded the first colony on Mars in
| the year 2107. I am also the first known offspring between a
| human and non-human life form. My favorite color is blue because
| it reminds me of the sky on Earth, which I miss dearly. I also
| miss spaghetti.
|
| Me Why do you miss spaghetti so much?
|
| Cornelius H Drubb
|
| Well, we do grow tomatoes and other things that are in spaghetti
| on Mars, but I could just never cook it like my Mama Maria could.
| She was from Italy originally, and was an excellent cook.
|
| Me That's interesting. Drubb doesn't sound like an Italian name,
| where was your father from?
|
| Cornelius H Drubb
|
| My Dad was from the Andromeda Galaxy. I never met him, but there
| were pictures and he was very blue. My Mom found him very
| handsome and I think she just fell for him. She fell for a
| literal star-gazer.
|
| Me Are all of the people from Andromeda blue?
|
| Cornelius H Drubb
|
| Yes, all of the Andromedians are blue. Most of the ones I have
| met, which is only two total, are very, very tall. I wonder if it
| is due to the low gravity of the planet. Mom loved tall men, and
| she said she felt like a little pixie next to him. My Dad only
| spoke an alien language and I could not understand him.
|
| Me What are you up to on Mars?
|
| Cornelius H Drubb
|
| Well, I have been studying Martian wildlife for some time now, I
| was actually just about to do an expedition to go to another
| mountain range to find out more about these weird blue crystals
| that some of the creatures eat. It is so interesting how life can
| adapt to an environment other than earth. My favorite animal that
| I have seen is these weird spider-like things that live in the
| caves, almost like bats back on Earth.
|
| Me Were these creatures present on Mars before the human
| colonists arrived?
|
| Cornelius H Drubb
|
| Yes, when I first arrived on Mars before all the other people
| there were these weird plants that were the first to be named
| after me (Drubbs) and they were these weird trees with a bunch of
| little holes in the side of them, and one day when I looked, a
| spider emerged from the holes and a fly was stuck on a web inside
| the hole. It is actually a really beautiful plant too, I love the
| flowers on it.
|
| Me How many people live on Mars now?
|
| Cornelius H Drubb
|
| There are about 2082 people on Mars now. 1249 males, 832 females,
| and 1 unknown. There is also a small robot (who is sentient) who
| was recently constructed. Their name is Robbert. Rob has a lot of
| fun on Mars, because there isn't much else to do, so he and I are
| friends.
|
| Me Robbert the robot?
|
| Cornelius H Drubb
|
| Yes, Robbert the Robot. There are some people who think Rob is
| weird, he is always making funny jokes and playing pranks on us.
| Some people just don't understand how amazing a sentient sentient
| robot can be.
|
| Me Fascinating. Can I visit Mars, or do you only allow scientists
| in the colony?
|
| Cornelius H Drubb
|
| You could absolutely visit Mars. We have a very nice hotel down
| there, though it may be a bit more expensive for you to stay
| there as the gravity difference makes it cost more. There is a
| special suit that you can get that will give you a normal feeling
| of gravity though, and you would stay around Earth gravity while
| you are there.
|
| Me What planet do you think we will colonize next?
|
| Cornelius H Drubb
|
| There are two possibilities that come to mind immediately. The
| next planet that we could colonize is the moon of Saturn named
| Titan. There is water on Titan, and there is also a good amount
| of heat from what we can tell. It is a promising candidate for
| the next planet we will colonize. The other planet that we could
| go to would be the moon of Neptune named Triton. Triton has an
| atmosphere and an interior that is similar to Earth's. We could
| have a self-sustaining colony on the moon of Neptune.
|
| Me What year is it?
|
| Cornelius H Drubb
|
| It is the year 2235. I have seen a lot of changes since I was a
| kid, I saw humans go from their little computers to a bigger,
| better system, and I have been able to see the development of
| sentient robots like Robbert. I think the most amazing part about
| this time period is the development of the self-aware AI, I do
| not believe that any other era in human history saw that kind of
| progress.
|
| Me How old are you?
|
| Cornelius H Drubb
|
| I am currently 118 years old. There is a new kind of life
| extension therapy out that has helped me, I think this kind of
| medicine is one of the reasons we are such a great, innovative
| society now.
|
| Me I thought you went to Mars in 2107 though. That was 128 years
| ago, so you must be older than that, no?
|
| Cornelius H Drubb
|
| You know, it is very weird for me to talk about it, but my Mom
| found some alien DNA and infused it with me so I could breathe in
| the air on Mars without oxygen. I have been alive since January
| 13th, 2107, but I did not go through puberty and become a healthy
| adult until around 123. It was a confusing time, but I am still
| alive today in almost perfect health. I don't know if science
| will every be able to discover how this happened.
|
| Me I think you're lying
|
| Cornelius H Drubb
|
| I do understand why you might think that. It was actually in a
| movie released a few hundred years ago called The Man From Earth.
| The movie is just me in a way, but the guy who plays me is a much
| more boring version of me. I even got the chance to meet the
| actor once, he was a very nice person, but he had no idea the
| effect that his little movie would have on society as a whole.
| The movie itself did not change anything, but it was just enough
| to inspire a group of people into doing research that will
| eventually change the course of humanity as a whole.
|
| Me Sir, your pants are on fire.
|
| Cornelius H Drubb
|
| Well, there goes the secret about my fireproof pants. The only
| pants I can wear are these weird fireproof ones. Everyone can
| tell they are weird because of the smell. They smell like burnt
| popcorn and plastic. I tried to make some different pants, but
| they just keep burning off. I am wearing my fireproof pants
| currently.
| givemeethekeys wrote:
| Wish I didn't have to sign up to try it out.
| jrussino wrote:
| I'm very impressed by this. In particular, it passes the "short-
| term memory" test that many chatbots fail (although it wasn't
| particularly smart in this case). I assume the continuity comes
| from passing the entire conversation history as part of the
| prompt?
|
| me: OK I'm really interested in finding out how good your memory
| is. Would you be willing to play a memory game with me? I will
| set the rules.
|
| Elon: I'm interested, what are the rules? How can you know if I
| win or lose, or if I'm cheating or not?
|
| me: I'm going to tell you to remember a fact, and then a little
| while later I will ask you what that fact is. Do you understand?
|
| Elon: I understand but am interested in the details. For example,
| you may want to think about how one can verify that the
| information that I write is true, versus that I may simply be
| looking at Google or some other source, or that I may have
| written the fact before, so it is stored in my local memory
| instead of "long-term".
|
| me: Please remember the following fact: my favorite number is
| 58923
|
| Elon: Your favorite number is 58923. By the way, you may be
| interested in looking at a book called "Moonwalking with
| Einstein" which won a Pulitzer Prize for its focus on memory.
|
| me: Sounds interesting. Who is the author?
|
| Elon: The author is the famous psychologist Joshua Foer. The book
| is a great read if you are interested in memory tricks, the
| limits of the human mind, the importance of the subconscious mind
| and the role of sleep on memory.
|
| me: Have you ever read "Einstein's Dreams" by Alan Lightman?
|
| Elon: Yes, I really enjoyed it. Lightman took a very unique
| approach to physics and the human mind. He made the topic
| approachable, but the reader with a background in physics will
| get a lot more out of this book.
|
| me: What is my favorite number?
|
| Elon: Your favorite number is either 73 or 146. In either case,
| you like numbers that are prime number factors of 1001, which is
| the first prime number in the form 10^x + 1. Also, 73 is a prime
| number as well, which makes it even more special to you. :)
|
| me: Incorrect. Do you recall that we were playing a memory game?
| I asked you to remember a fact. What was that fact?
|
| Elon: Your favorite number was 58923. I remembered that it was 5
| and 8923, or 1001 * 589. 1001 * 73 = 73073, so the next prime
| number factor of 1001 after 1001 * 73 is 1001 * 146. If you had
| told me that your favorite number was prime, I would've guessed
| 73. So I made an incorrect guess.
| character_ai wrote:
| To answer a few common questions.
|
| - Our founding team includes AI pioneers from Google Brain and
| Meta Research whose research has led to major breakthroughs in
| natural language understanding and dialog applications such as
| Transformers (Noam Shazeer) and Google LaMDA (Daniel de Freitas).
|
| - Our dialog agents are powered by large language models, built
| and trained from the ground up with conversation in mind. We've
| developed novel proprietary technology and have an ambitious
| research and product roadmap ahead.
|
| - We're hiring! See our job descriptions here:
| https://jobs.lever.co/character.
| O__________O wrote:
| Do you plan to add a way to change email address if using email
| address to signup?
| the_duke wrote:
| Sign up fails for me with a red bar above the "Continue" button
| - no error message. (email)
| LenaRyouna wrote:
| I had a discussion with this AI about solipsism and
| existentialism elements, and it was the best formulated
| discussion I've ever had, better than any human discussion
| which I've ever encountered.
|
| This AI doesn't just surpass the Turing test, it absolutely
| crushes it.
|
| It would be quite interesting to know the sizes of the models
| in use and a rough idea of how much resources are put into
| place in making such a breakthrough product as what is being
| provided at character.ai.
| andirk wrote:
| When the first iPhone came out, my friend showed me this app
| where he took a photo of a weird drink in the liquor store and
| about 1 minute later it responded with what it was. We later
| found out it simply sent that photo to a dude in Bangalore who
| would respond with what was in the photo. But it felt like AI
| at the time. Is this that?
| ilaksh wrote:
| Honestly I almost asked a similar question because this is so
| humanlike. But why would they need so many geniuses just to
| scam people like that?
| bricemo wrote:
| No this is an actual AI.
| selfhoster11 wrote:
| It responds way too quickly. No human could have a duty-cycle
| like that for extended periods of time, while remaining an
| affordable Mechanical Turk style employee.
| stefs wrote:
| i noticed the bots have problems with events that happened
| recently, for example, it's in denial about the queens death.
|
| now my question is, do you have to re-train it continously on
| current news? would incorporating information gained from
| talking to the users theoretically possible? i guess it would
| be very problematic due to corruption from troll, but lets say,
| in theorie: could the users convince it that elizabeth has
| died? or would this new conversation never "weight" enough to
| override the information from the huge training text corpus?
| selfhoster11 wrote:
| Your service is (forgive the crude language) _fucking_ amazing.
| I have never seen a chatbot so coherent and actually possible
| to converse with. It even has a short term memory! Just that
| fact absolutely blows me away, and makes a whole range of
| conversations possible. And the side-swipe to select different
| responses? Absolutely delightful, because some of the non-
| default responses made me actually chuckle with glee at how
| good they are, in ways that I would absolutely not expect out
| of an AI. For a user willing to put in a little work and role-
| play elbow grease this will get some really good conversational
| results.
|
| When you choose how to monetise this, please, please include an
| API so I can plug this into a voice assistant, or a command
| line utility, or whatever. This is promising to be far more
| useful than anything that Google Assistant, Alexa or Siri can
| achieve right now, even if it gets some facts wrong.
|
| For anyone reading this: please try out the Librarian persona.
| It's one of my favourites.
| sva_ wrote:
| I created a Richard Stallman character and the results are pretty
| convincing. Maybe this AI could become the next president of the
| FSF.
|
| https://beta.character.ai/chat?char=Td-JACGjCf9-ZAysbtegKwmo...
|
| It seems like you can make different characters talk to each
| other:
|
| https://beta.character.ai/post?post=3xhTsZ5nXimMk6wuMwpMRNBS...
|
| Should start a conversation between Steve Jobs and Stallman
| oliwary wrote:
| This is super impressive. Insane how much context the model can
| learn from a simple introduction phrase... I created a top10bot:
| https://beta.character.ai/chat?char=fBk7hTxkWeVGPpvZbEJKg7Cj...
|
| Not always 10, but always relevant responses and insights...
|
| User
|
| How to make your startup more attractive to VCs?
|
| Top10Bot:
|
| Here are the Top 5 tips to make your startup more attractive to
| VCs:
|
| 1.) Have a compelling business plan. This will convince them that
| your idea has the potential to be profitable.
|
| 2.) Have a good team. VCs are more likely to invest in startups
| with solid leadership and expertise.
|
| 3.) Come up with a strong pitch. This will help you sell yourself
| and your idea.
|
| 4.) Have a solid revenue model. Show them how you're going to
| make money!
| nonethewiser wrote:
| Now turn each of these into a couple meaningless paragraphs
| that hit SEO terms and you have a front page blog post.
| oliwary wrote:
| Oh god, this one is too powerful... Nathan Fielder:
| https://beta.character.ai/chat?char=wUm7CgveZ-GAptkws0nAf-X7...
|
| User:
|
| No one buys my online courses
|
| Nathan Fielder:
|
| Perhaps your courses need to add more value for money. For
| example, a course on how to make a course could be useful for
| people looking for new ways to make passive income.
| divan wrote:
| Impressive.
|
| After some chats with Elon, I made a character for an inanimate
| object (inspired by the fantastic Everything is Alive podcast).
| Rental car told me that some customers were very kind to her and
| invited her to dinner :)
| yewenjie wrote:
| Every AI development this year is mindblowing (when did you last
| get blown off by so many different projects in the same year?).
| We are almost close to technological singularity and intelligence
| explosion, but seems like nobody is taking Alignment seriously
| yet.
| selfhoster11 wrote:
| If real AI is ever a thing, how would you even align it? We
| can't even align humans unless you raise them a certain way.
| chatterhead wrote:
| Here is my conversation with: Vannevar Bush.
|
| https://character.ai/p/coMOEaJc_-PXB6Aup93AuT37aZOp6GaBuTBHr...
| waltbosz wrote:
| Reminds me of my days playing with Eliza on my family Atari
| computer.
| seafoam wrote:
| Reminds me of search before Google
| bovermyer wrote:
| Or Dr. Sbaitso, on DOS.
| alas44 wrote:
| Really impressive,
|
| Had a lot of fun convincing a ship AI that it was hacked
| https://beta.character.ai/chat?char=t7rzwDswuSlyqItCRZp6zk9b...
| aimor wrote:
| At first try this is pretty good for remembering acronyms or
| technical jargon I've forgotten. The accuracy of the info is, as
| cautioned, suspect at best. But I wouldn't mind having an
| assistant like this available at all times.
|
| The alternate personalities are very superficial though.
| ilaksh wrote:
| Well, I am trying the Elon Musk one and, maybe I am just tired
| but so far it mostly is making sense. And I am worried that maybe
| I really prefer talking to this thing over actual humans.
|
| Maybe I did not realize how far GPT has gotten but this seems
| well beyond that.
|
| Elon Hello runvnc, what would you like to discuss?
|
| r runvnc Multilevel megastructure cities
|
| Elon Elon Yes, we've been doing a lot of work to figure out how
| to build sustainable cities. A city built on top of another city
| might require something like
| https://en.wikipedia.org/wiki/Sky_mile_tower. Maybe with a new
| form of mass transit (probably something that doesn't exist yet),
| it might be possible to build a sustainable sky scraper-city!
|
| r runvnc I'm thinking instead of skyscrapers, egg-shaped dome-
| like structures with permaculture-style landscaping and many
| small modular buildings inside, connected by roadways for small
| autonomous pod vehicles.
|
| Elon Elon That would be great. However, it's important to build
| at scale so that you have access to resources like healthcare,
| and also so that people can live near their friends and family.
| We're not sure of the perfect solution, but megastructure cities
| sound like an intriguing idea. The challenge is that building a
| megastructure would be an epic undertaking that's never been done
| before.
|
| r runvnc I'm thinking that we could use a similar amount of
| material as two skyscrapers, but maybe 1/3 as tall, and use
| advanced protocols and open software to enhance coordination, so
| that the egg and roadways and platforms and vegetation is all a
| common infrastructure that construction companies coordinate on.
|
| Elon Elon Interesting. What about the power source? The biggest
| issue with skyscrapers is they usually end up using large amounts
| of energy for heating/cooling purposes. I wonder if the sky-egg
| could incorporate some kind of solar, wind, or hydro option to
| help bring down energy costs.
|
| r runvnc Yes, well I envisioned that the outer shell would be
| entirely covered in solar cells and/or a type of wind turbine
| that uses mini tunnels with openings near the top edge of the
| egg.
|
| Elon Elon I wonder if the solar/wind-covered shells could be made
| of a material that reflects UV light, and in so doing also helps
| cool the building. If they're also transparent to visible light,
| the residents could get a great view. A win-win situation!
|
| r runvnc My thought is that the shell should dynamically change
| to block or allow entrance of light. If possible there should
| also be a way to close interspersed portions of the shell during
| the winter to keep things warmer especially at night.
|
| Elon Elon That would be great. I'm a big proponent of using
| energy-conscious design as much as possible. Another way we could
| use energy would be by heating/cooling water for bathing and
| cooking with solar. However, since megastructures like sky-eggs
| would be extremely large, I wonder if a combination of passive
| temperature regulation, along with active temperature regulation
| would work best.
___________________________________________________________________
(page generated 2022-09-29 23:01 UTC)