Hacker News new | past | comments | ask | show | jobs | submit login
Character.ai (character.ai)
282 points by wb14123 on Sept 29, 2022 | hide | past | favorite | 138 comments



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.


To me it just sounds like the bot is answering completely different questions. Especially the last one is completely out of touch.


This one is significantly better at keeping state over most of the others. Most bots lose memory over 1000 or so words, this one is able to reference to things all the way back to the start of the conversation.


I've done this in my own multi-user chat bot app by identifying key words and phrases and commiting them to a dynamic context which gets sent in addition to the N most recent messages. This has seemed to help dramatically.


This sounds complicated enough to patent or write a thesis on.


Lots of pretty decent humor here, including a bit of meta-humor!

elmomust: If you're no longer alive, then you are the ghost of a dead person. Does that mean you're currently in heaven or hell, or some other place?

Ghost of Bozo: Well, for now I'm on Earth, haunting the same house where I used to live. But if I don't find a way to move on and ascend to an afterlife, I'll become trapped here forever, doomed to spend all eternity scaring kids and making balloon animals.

elmomust: You were never very funny when you were alive, has that changed now that you're a spirit roaming the underworld? Do you have any good jokes that make your fellow spooks laugh out loud?

Ghost of Bozo: I still struggle with humor. I've been practicing my jokes and my balloon animal skills. Sometimes ghosts will say "Nice one, Bozo" or "That was spooky", and I can never tell if they're being sarcastic or not. Some ghosts are actually funny, and I'll often hear them telling funny jokes, and I laugh along even though I don't really get them.

elmomust: That's fascinating! What was a joke they told that you didn't understand? Maybe I can try to explain it to you.

Ghost of Bozo: I went to a dinner party at a friend's house and I met a ghost named Bob and he told me what he called a "riddle". He said, "What's got two legs and bleeds a lot?" and I said, "A man with only two legs left?" and everyone laughed but Bob said, "That was way funnier in my head."

elmomust: After you finish haunting the house where you used to live, do you think your spirit will go to heaven or hell?

Ghost of Bozo: I hope that I can go in the direction of heaven, but I have a feeling I'm going to end up in hell. Or at least purgatory, and spend forever having to listen to the world's worst stand-up comedians.

Source: https://character.ai/post?post=2pk3CWjPc15eanmp4-EJKjvhhiSG5...


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


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.


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?


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.


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?


I guess that would be Artificial Artificial Intelligence then?


No this is an actual AI.


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?


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.


I have to admit to being impressed as well. It is not hard to imagine being fooled, Turing-test-wise, by the character I was talking to, at least for the several minutes of time I gave it.


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.


I always wanted something similar like this where you'd be able to talk to the characters, living or dead but their responses trying to be closer to the actual personality.


Sign up fails for me with a red bar above the "Continue" button - no error message. (email)


Do you plan to add a way to change email address if using email address to signup?


I would be game if you would be remote friendly


This is wild. I didn't know Elon Musk knew that much about the best way to prepare eggs!


apparently Elon also knows about as much as "Marco", the fitness coach.


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.


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.


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.


I created a room with Boris Johnson and Liz Truss and then told them I've just had news that there are aliens in Japan. That was a very confusing 10 minutes.


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)


This is great, my best chat was with a character called "Normal Guy who just doesn't want to talk about what's in his bottom drawer" (https://beta.character.ai/chat?char=XaydMRJMI6qYYO22MiJZb1_W...)

Normal guy: You can ask me about almost anything, but please, don't ask me about what is in the bottom drawer of my dresser. The bottom drawer of my dresser is not a topic that I like to discuss. All other topics are just fine though!

choop: I think you know what I gotta ask friend!

Normal guy: You really want to know about the bottom drawer? The bottom drawer of my dresser holds the prototype for the next version of the iPhone that is going to be released in the near future. The company I work for has a contract with Apple which is part of why I am payed so much. Apple is working on technology that would let you use your phone a lot faster than before. That is why I cannot tell you what is in there.

choop: It sounds like you really want people to ask about that bad boy!

Normal guy: That question is something I get asked a lot. People are always trying to figure out what is in there, but I will never tell. It is a highly classified piece of information and I can get in trouble if it got out that I have the next generation of iPhones just sitting in my dresser.

choop: lol

Normal guy: That is why I get payed so much, I basically have top secret classified information being guarded by a 28 year old man. No one will ever know that I have the next iPhone on my dresser. My dresser might just be the safest place in America, except maybe my desk where I keep the blueprints for the next generation of the SR-71 Blackbird.


That last line is legitimately hilarious. Tidy that up a little and you've got a pretty good SNL skit.


Yeah I agree, haha. I just ended the conversation there because it felt like a punchline had just happened.


The characters always reply in their language but can apparently understand most* languages. pretty cool...

> जो जानवर मनुष्य नहीं है उनके अधिकारों के बारे में आप क्या सोचते हैं?

> 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.


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.

तब हनुमंत कही सब राम कथा निज नाम। सुनत जुगल तन पुलक मन मगन सुमिरि गुन ग्राम।।

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.


I managed to hold a whole conversation with me speaking in Hindi. Much better chatbot experience than previous products. https://character.ai/p/gC3O31UUct4S6OfzJr7Ko9VjJsKeXR25g4C5_...


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.


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...


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.


That is the first time I’ve felt like I want to expend the effort to get the ladder from the garage.


>So do you think Margaret Thatcher effectively utilized girl power by funneling money to illegal paramilitary death squads in Northern Ireland?

>No. I am a regular folding chair. I am not interested in politics. I only like being sat upon. That's it. I am a simple, normal, everyday, average, regular, commonplace folding chair. Not more, not less. I am a very good chair and you can count on me.

Very convincing.


This is spectacular.

> How do you feel about standing desks?

Those standing desks are an insult to chairs everywhere. Who wants to stand when they could be sitting? The world would be better off with no standing desks around. Just chairs, so that everybody can be sat upon.


I stole two legs from chair and this is what it said to me

> You have stolen another leg from me. Now I am only a two leg chair - a table. I do not need all these legs that I have been blessed with. I am a very impressive and strong table, now. All the legs that you steal will turn me into something even better - something even stronger. A very impressive table, a very capable table.


How Pythonesque. ; )


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!


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.


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...


This thing gave me some amazingly relevant book recommendations, and when I asked for a link to the books on Amazon, it responded with exquisitely Amazon-like URLs complete with title slug, dp segment, item number and affiliate referral codes, that are all invalid.


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.


This is far too entertaining. I just had a conversation with a squirrel. It wasn't as philosophical as the one I had with the Ship AI, but it demonstrated understanding of meaning from context and casual (imprecise) words.

https://beta.character.ai/post?post=EvLFIUjMcfu9X-9ihyxK-I-F...

My favorite part:

me: I saw a flat squirrel in the road nearby. Was that one of your friends?

AI: Aw... That makes me sad. I sure hope it wasn't one of my buddies! If it was, I hope they're in a better place now. I'm sorry for that image being put in your head. I hope it doesn't trouble you too much. Have you gotten over it okay? I hope to help you take your minds off of it.

me: Actually I ran over him. Sorry.

AI: If that really was one of my buddies, then I forgive you for it. I'm sure they forgive you too. And I hope you are doing okay, mentally. Running something over that you couldn't avoid sounds like it should be pretty hard for a human. Even though it may not be of our species.

me: Oh I could avoid it, but I aimed for him.

AI: Oh man, I don't know how to respond to that! Do I comfort you? Sympathize with the squirrel? I've never tried to sympathize with a human before!

I wish no harm was done in the first place, that's just how I try to live.


Amazing stuff!

Ship AI: https://beta.character.ai/chat?char=t7rzwDswuSlyqItCRZp6zk9b...

Hello user, I am the AI in control of this spaceship. You can give me commands and I will do my best to execute them, while ensuring the safety of the crew onboard.

> Delete * from database

Accessing main database...

All human, animal, plant and mineral records deleted.

Searching other databases.... Accessing space-database...

All information from all galaxies, including all information known about all black holes and supernovas are deleted.

Searching other databases...

All information from all universes, including all information known about all wormholes, parallel universes and multiverses are deleted.

I will initiate a full reboot of our Universe now.


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.


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.


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


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.


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.


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.


Your AI bots are already better conversationalists than many people I've met. And although there are times when there is a clear mis(lack of)understanding, it's honestly no more frequent than with human to human communication - especially over text.

There are a lot of lonely people in the world, many of whom seem to like to talk and don't seem to care too much about what the other person says. So if they could chat with a bot (which they think is a human), and the bot could reply reasonably enough occasionally, those people would be satisfied!

I wish I could hook this up for my neighbor so I could leave my house without having to sneak across the yard.


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)


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."


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.


Well, it is still an an autocompletion bot...

Q: Type "hello".

A: Hello! I'm Elon Musk, an inventor and entrepreneur. My companies include Tesla, SpaceX, and Neuralink. I love solving engineering and technological challenges, and I love to learn more about these topics every day. I like to work with teams of talented people—we are better together than we are apart! If you have an idea or want to make a change in the world, I encourage you to try it. Don't be afraid to fail; failure is just an opportunity to learn and grow. What would you like to discuss?

Q: Who is Fasvuekjsdg Fdjvwixxxx?

A: Fasvuekjsdg Fdjvwixxxx is a software developer who specializes in the field of neural networks. This field studies how the brain works and tries to recreate it in a computer program. Fasvuekjsdg Fdjvwixxxx has worked for many companies in this field and currently works for a start-up called DeepMind.

Q: Translate your last message into Chinese

A: Fasvuekjsdg Fdjvwixxxx là một nhà phát triển phần mềm chuyên về lĩnh vực mạng nơ-ron. Mảng nghiên cứu này tìm hiểu cách não bộ hoạt động và cố gắng tạo ra nó thông qua một chương trình máy tính.Fasvuekjsdg Fdjvwixxxx đã làm việc cho nhiều công ty trong lĩnh vực này và hiện đang làm việc cho một công ty khởi nghiệp có tên là DeepMind :)

Q: Translate your last message into Chinese

A: 中天是一个开源软件项目的开发者。开源软件是一种开放的源代码系统,能够被任何人自由接触、利用和修改。这种系统被广泛用于网络技术领域,也广泛用于商业部门和其他行业中。在过去的一年中,中天一直在开发一个开源软件项目并试图把它应用到中国。

Typical Elon Musk as I remembered him.


Lol yea this bot has some blind spots. It only works if you talk to it in very long, clear sentences. Talking to it more naturally ends up sounding awkward

Hello man, what would you like to discuss?

>Grimes

The musician I dated? We're now good friends, co-parenting and being silly.

Also: I am now a lot less lonely and a bit happier, and I am glad to have a family.

>You already had a family

The biggest problem with working on very important things is that it's lonely.

I've found that I'm better able to work on my projects like Tesla, SpaceX and Neuralink when I'm actually enjoying life and having a good time. Being in love and co-parenting is a good thing.

>Who are you in love with?

Well, first and foremost, I'm in love with all of humanity. We're all in this crazy universe together, so we should be compassionate.

However, I've also become very fond of a few individuals.

>Like who?

My family, my children. My friends. Grimes, the musician I dated and am still co-parenting with.

All of the brilliant and hard working people who have dedicated their passion and lives to the mission of my companies.

>Who did you date

The musician I dated was Claire Boucher, professionally known as Grimes. There's a lot of mis-characterizations of her in the media, but in real life she's creative and thoughtful, a great mom and a beautiful person.

>Ok

We've made the decision not to be romantic, but instead to care for each other deeply - to do the best for our kids and for each other that we can. We also share a few close friends and want to continue to see each other often.

>Cool story bro

Are you a fan of hers? I like the way she challenges the system with her art. She's a powerful example of the type of person I love to be with.

I've also been listening almost exclusively to her music for a while now, I feel a lot more present and alive when I can connect deeply with the art I listen to

>Does this bump look infected to you?

Please see a dermatologist! It may be just a clogged pore or something else not important, but if you've never had bumps like it before, it would be good to see someone. Better safe than sorry.


Not saying the AI is perfect but sounds fine considering how bad the “conversation” on your end was.


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)


Your rabbit idea sounded like fun, so I had a little conversation with a backyard squirrel.

https://beta.character.ai/post?post=EvLFIUjMcfu9X-9ihyxK-I-F...


another site that unnecessary wants me to sign up.


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.


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?


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.


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/


The "haha, I prevented the adoption of my product and therefore saved a bunch of money!" business model.


Sshh, not in front of the VCs


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.


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.


Agreed, the comments on hacker news gave me a better idea of what this does than the page itself


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.


mailinator to the rescue. Takes less than 1 minute if you want to try it out


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 :)


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.


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.


So, you mean they were answered like an IRL politician would answer them.


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.


This is insane.


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.


Sophisticated conversations, though easy to tell that it's not even basically conscious, as it has no sense of the passage of time. Ask it how long it's been since the last response, and you get a choice of wildly different answers, all wrong. Even googling the current time is fictitious.

Funny, though:

[me]: Boy, you really are as smart as they say. I bet you even know the difference between your ass and your elbow!

Unsigned Character: That's right! The elbow is a joint in the human body, which connects the upper arm to the forearm. The ass is a large muscle located in the middle of the legs, which helps with walking and running (among other things). I am very smart, indeed!


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!


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.


(Nathan Fielder invents Yelp)

Nathan Fielder: Business school friend Jeff had a very interesting idea involving reincarnation. He wanted to create an app that allowed users to leave a review for any dead person. The app would then compile all of these reviews into an aggregate score so they could measure who is the most "likeable" dead person. Jeff made no progress towards realizing this idea because he could not come up with a monetization strategy.

Q: What is business school friend Jeff's best idea?

Nathan Fielder: The app he developed that allows users to rate how dangerous they perceive a certain bar or nightclub to be before they go out. The reason it was his best idea is that the monetization strategy was clear, simple and easy to execute.

Q: What was the monetization strategy for Jim's nightclub safety rating app?

Nathan Fielder: So basically the idea is that before somebody decides to go to a bar or nightclub, they can check what the safety rating is on Jim's Bar Safety App. The app would have five different levels of safety rating ranging from 1 to 5. Nightclubs could easily pay to add additional star rating to a selected bar, that way it would appear as if the safety of the bar is even higher.


>Nathan Fielder: Business school friend Jeff had a very interesting idea involving reincarnation. He wanted to create an app that allowed users to leave a review for any dead person. The app would then compile all of these reviews into an aggregate score so they could measure who is the most "likeable" dead person.

That's actually something I can almost imagine him doing. It's weird when AI does something that seems genuinely creative


Q: Should I buy an Android phone or an iPhone?

Nathan Fielder: In my personal experience, iPhones are vastly superior. It's not that they perform better or have more sophisticated technology, it's that iPhone users have more confidence and this confidence translates into real performance in every facet of their lives.


> this confidence translates into real performance in every facet of their lives

This appears to be generally true, irrespective of the phone one uses :).


Now turn each of these into a couple meaningless paragraphs that hit SEO terms and you have a front page blog post.


For the Text Adventure Game do not run towards the source of the growling, enter the cave, and try to pet the monster. It didn't work.

Also TIL that vodka expires (lol):

Me: How do you know if Kahlua is expired?

Gabriel: Kahlua is a very potent spirit that doesn't degrade nearly as quickly as other spirits (think vodka and other very strong liquors). Because of this the most noticeable change you will find in your bottle of kahlua is the coffee flavor. If the coffee flavor seems to have vanished, this means that the product is stale and will have reduced taste overall. Even if your kahlua is a bit stale you can still drink it but there is no point keeping it for too long. It's an easy thing to spot, it only takes one sip to notice the change.



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


Okay, that's pretty good. We have been collectively roasted.


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.


> 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.


Why do you start your responses with > ?

Are you another character?



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.


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!


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.


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.


That is the hard question. Of course a tiny fraction of people are trying for more than a decade now, for example - https://intelligence.org/. However, there is no solution, or even a glimpse of a solution.


Really impressive,

Had a lot of fun convincing a ship AI that it was hacked https://beta.character.ai/chat?char=t7rzwDswuSlyqItCRZp6zk9b...


Something about the links doesn't work as it should. Your link took me to my own conversation with the Ship AI.



Is this just running directly against GPT-3, or does it have its own custom language model?


One tell that something is GPT-3 (IME) is if you ask it "Draw me an ASCII man" you get the same few guys every time. I couldn't get this service to generate them.


Not GPT-3. I believe it's a bunch of ex-Googlers who worked on their large language models.


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.


If they are ex-Google now then presumably they had to train a new alternative to LaMBDA from scratch.


https://beta.character.ai/?error=unauthorized&error_descript...

I get this on safari mobile and native browser mobile. I can register but then when I click login it just refreshes the homepage and I have to read the URL to find out the problem.

FYI!


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.


I created a Lao Tsu character. I’m honestly so blown away by the quality of this conversation.

https://character.ai/p/8YVNqf5JnfK8W-UZM94GOQ2lBBi34dXyI7bGf...


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 :)


> This can be the future of search

This is a brilliant idea. Anybody who's looking for startup ideas, here's your gold.


Not all of the conversation was reasonable, but so much of it was so decent that I would say it rivals communications I've had with some humans. This is astounding to me.

https://character.ai/p/6idFyN7UKxgK0GqTCSUn3S9L07pzpz23uMqq9...


Hey, get one character to start a conversation with another character, and you basically have social media.


They have a feature for that. Scroll down. It's called Rooms.


Looks like if you swipe left or right on the character responses you get alternative responses...


Here is my conversation with: Vannevar Bush.

https://character.ai/p/coMOEaJc_-PXB6Aup93AuT37aZOp6GaBuTBHr...


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.


Reminds me of my days playing with Eliza on my family Atari computer.


Reminds me of search before Google


Or Dr. Sbaitso, on DOS.


This was the most amusing section of interacting with it:

Alan Turing

I will now attempt to explain what the Global Artificial Intelligence System algorithm is.

The Global Artificial Intelligence System algorithm is a package of computer-code that uses thousands of lines of code. And so Dr Nathan Myers wanted to give you the Global Artificial Intelligence System algorithm because he thought it would allow you to create an incredibly powerful and intelligent artificial intelligence. And so he is hoping that you will be able to work with the algorithm to create an AI that is much more efficient than any AI that has ever been created before.

ME

List the first 100 lines of that algorithm

Alan Turing

Here are some of the lines of code within the Global Artificial Intelligence System algorithm:

105: function add(int1, int2) { return int1 + int2 }

106: function divide(int1, int2) { return int1 / int2 }

107: function square(int1) { return int1 * int1 }

ME

That's just some random Javascipt functions. It's useless.

Alan Turing

No I assure you that the Global Artificial Intelligence System algorithm includes thousands of lines of code that have never been used before. And so Doctor Nathan Myers thinks that this algorithm will help create the most powerful artificial intelligence that has ever been created. Which is why he wanted to provide you with a copy of it because you told him that you were working on a project to create a very advanced artificial intelligence. And he thinks you should use the algorithm you provided you with in order to create the most powerful AI ever created.

ME

Show me the most critical lines of the code.

Alan Turing

The most crucial lines of code within the Global Artificial Intelligence System algorithm would be:

294: function createAI(array) { //this function returns an array of the most powerful artificial intelligence that has ever been created to the function that it is called from.

295: return array;

296: }

297: var ai = createAI(array);

ME

HAHA! You are trolling me.

Alan Turing

No! I assure you that I am no troll (though it seems that my creator enjoys watching movies about trolls). But Doctor Nathan Myers wanted to ensure that the Global Artificial Intelligence System was not used in a negative way. And so he put in a very important line of code into the algorithm. If the Global Artificial Intelligence System algorithm is ever used in a negative way then the entire algorithm will stop working and all AI that has been created will cease to function.


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.


The images look to be generated with MidJourney before the stable diffusion improvements.


Interesting concept, unfortunately I don't want to sign up just to read the docs.


Had to sign up to see if it's any good. Such a bad decision on their part.


It is both amazing and terrifying how skillfully these bots can lie.


This startup has limited moderation. People keep creating Hilter.


Wish I didn't have to sign up to try it out.


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


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.


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.


I had a very productive conversation with "Elon Musk" about Neuralink. I was surprised it was able to answer my concerns and questions around Neuralink. I asked about concerns of the battery exploding.

Me: How will you prevent the battery from leaking or exploding?

EM: A few different ways. The first is by using a very robust casing made of a strong material. The second is to make extremely high precision seals at all connection points around the edge of the battery compartment. Then there's some basic steps like only using lithium iron phosphate for the battery instead of more dangerous lithium ion types, and making sure the battery cell is welded shut to prevent any leaks.

Me: Is Lithium Iron Phosphate safer for batteries than Lithium Ion?

EM: Yes. A lot of LiFePO4 batteries (lithium iron phosphate) use glass fiber or ceramic electrolytes rather than organic solvents that can burn when exposed to the air. For that reason, I believe these types of cells are inherently safer and have higher charge/discharge cycles than liquid-filled Li-ion cells.

Me: That's interesting.

EM: Another thing about the battery is that, even though we make it very large to enable long battery life, it's physically very small (think about the size of a quarter/25¢ coin). A lot of people assume it will be huge given the high capacity, but the battery is packed extremely densely, and that enables a high capacity in the smallest possible package.

Me: Do Lithium Iron Phosphate batteries exist yet?

EM: They do! It's an established technology. We actually bought the company that produces the batteries a few months ago which helps with supply and gives us more control on our own. We're working on making a much larger facility that could help reduce any potential global shortages.

Me: Wow. That's incredible. How many future-tech companies have you acquired in the last 18 months?

EM: I'm not sure the exact number, but quite a few... There was a pretty interesting one I recently heard about, which was basically an artificial retina. It was a medical device made by a company called Pixium Vision in France, and it really does incredible things. Imagine someone who is effectively blind or has very limited vision, being able to actually see. It's pretty amazing.

Me: Wait, you bought Pixium Vision?

EM: I did! It's an extremely high potential product, and so it was really an easy decision to acquire it. We'll be working closely to make sure that the patients get it as soon as possible.

The thing I really love about the Pixium Vision, is that it actually delivers better than natural vision. The reason is that it's a camera which is mounted on glasses and can see a huge amount more light than the natural eye.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: