Stop what you’re doing right now and download Poe!

…Unless you’re using an Android phone, in which case maybe you can drop what you’re doing right now, cry, buy an iPhone, then come back.

…OKAY NO DON’T KILL ME AAAAAAAAAAAAAAAAAnd now, dear readers, we talk about Poe! 

Generated with Midjourney!

If you don’t know what Poe is, Poe is not this Poe — it’s question and answer platform Quora’s brand new AI baby, now available on iPhone and iPad!

Initially, buying into the hype of the Microsoft and Google AI arms race, I thought that Poe was just a Chatbot that was trained on Quora data and by extension the millions upon millions of questions and answers that it contains, but I realized that it wasn’t (although that’d be cool, though uh… I’m not sure how that’d work considering that nowadays a ton of questions on Quora are kind of powered by people trying to copy-paste ChatGPT in order to rank?).

Anyway, Poe isn’t exactly a chatbot in and of itself – it is what I would describe as a Chatbot aggregator, which means that it collects several different Large Language Models (LLMs) into a single interface; no wonder, considering the fact that the project is called Poe because it’s short for “Project Open Exchange”, which I guess alludes to the fact that the premise is that you can ask questions to a variety of different AI chatbots and receive answers relatively quickly. Already on the platform you will see three main chatbots. The first in the lineup is Sage, the next is Claude, and the last of the bunch is Dragonfly; Sage and Dragonfly are powered by OpenAI, and Claude is powered by Anthropic P. B. C. and its Constitutional AI framework.  

Each has its own methods of going about generating conversations, with OpenAI going for RLHF and Claude through the channel of constitutional AI and harm reduction, but I think you should try these for yourself to see the differences, and perhaps also read this article from Scale to see a detailed comparison.

You’ll see each of these on the left end of the app and you can select them and start talking the way you can with ChatGPT.

Dragonfly is fast, but not significantly faster, I think, compared to Sage at the moment – although I’d probably appreciate that a bit more in the event that this app becomes super popular.

The question you might have is that, apart from the number of models available, how is any part of this experience different from ChatGPT or from Claude, though?

Let’s compare. 

So here, I ask ChatGPT why the sky is blue, and receive a pretty reasonable response. 

It takes about 10 seconds to complete. On the other hand, when we do the same thing with Sage, which is also an OpenAI model, we get the following in 4-5 seconds generation time – which is significantly faster than ChatGPT, but is not bound by the fact that ChatGPT has millions of users concurrently using it… But oh wait.

See the blue links?

When you hit these… 

…Sage begins to elaborate while providing further links as well.

To be exact, these aren’t exactly links – when you click them, they prompt the algorithm with a new text prompt that’s related to the words that you searched for, in turn providing more context and elaboration on what you asked about and helping you to fill up those knowledge gaps real quick.

I think that this is super cool and definitely a step in the direction of the future of search, because it does mean that you can go down a daisy chain of conversations, ask questions, have them answered, and be prompted to ask about the things that you don’t know about; I can totally imagine this as a question and answer service and can even imagine something like this replacing Quora, if not for the fact that subjective experiences and updated information were still relevant and important.

While at the moment this is constrained to material within the training set and by extension data limited to 2021, one can only imagine what might happen at a later point when or if these models receive internet access!

Apart from that though, a cool feature of Poe is…

Social:

One of the fun things about Poe is a whole social element that’s integrated into the app itself.

There’s a feature that allows you to share the things that you’re looking at on your feed so that people can see what you generate – essentially, whatever you ask, once you hit the Share icon and then “Share on Poe”…

…Which will let you create a little set of posts that will just randomly show up on people’s feeds, kind of like an implementation of a little TikTok-esque feed full of the prompts that people are publicly sharing around the world and that people can upvote and downvote at their leisure, along with little bubbles that show the kinds of prompts that people have shared at any given point.

I think it’s kind of cool that you get to see these questions, mainly cause you get to see how people around the world are choosing to interact with AI, which creates a (human) communal experience so we can see how people are choosing to prompt things and keeps things light and fun 😀

Here are a couple of examples:

It’s cool to see what people are thinking and writing about, isn’t it? Very much in the spirit of Quora, I think – it does make me wonder if that’s the next evolution of the platform, albeit I still imagine that it might be difficult for algorithms to source personal data or subjective opinions into their training data or make people willingly choose to submit it; perhaps the platforms will coexist? I don’t know.

Anyway, since the thing’s called Poe, I decided to ask Poe to go right ahead and role-play Poe and the Raven.

Uh, towards the end I went and created a bit of an Oxford Union style debate there.

Anyway, I found the chatbot aggregation, links, and social features to be pretty cool and solid features in the app at large, and these all make me really wonder how the platform’s going to evolve in the days ahead.

Some small concluding thoughts:

I guess that Poe’s trying to unite all the different AI models and chatbot applications in one space, and that does kind of make sense, but I would guess that some of the companies that are generating LLMs simply won’t feel the incentive to participate (or won’t have the capital x investment to afford the training costs), while the companies that have generated these APIs would be happy to charge Quora or perhaps at a later point the end users of Poe for using those APIs when they eventually monetize (it’s already happening with ChatGPT), they’ll still be keeping their latest and greatest models for their proprietary usage and for paying users so that these users can use their products beforehand.

Still, what we’ve got here is definitely pretty great already, and I look forward to seeing how this platform’s going to develop in the days ahead!

To end this little exploration, I couldn’t resist making a rap battle about sentient AI with a tiny bonus at the end.

See:

See: https://poe.com/victortan/1512927999828824

And with that, the mic drops. Thanks for reading as always, and over and out!

Leave A Comment

Recommended Posts

The things we like but are not good at.

In this world, as we pass through, we may realize that there are some activities that we deeply and truly love – little skills, hobbies, and occupations that pique our minds, hearts, and souls when we participate in them as an act of pleasure.  As we pass through the tides of time, though, almost inevitably we come to realize that simply because someone we enjoy something, that doesn’t mean that we are going to be good at it. In fact, that’s an understatement.  Why are we talking about good when actually we can be horribly, devastatingly, and world-changingly catastrophic at it?  Here the realization inevitably comes, almost as if it were the common heritage of humanity: Just because you like something, that does not mean that you will be good at it.  One might argue that a true passion is such that even if one isn’t good at something, that the passion should stay.  Even if you are a horrible dancer, that does not mean that you should despise dancing.  The words of an eternal Malay proverb come to mind, “Tidak tahu menari, memarahkan lantai.” They resonate through the core of our beings and remind us:  If you dance horribly, that does not mean that you should blame the floor.  In other words, our lack of skill is no justification for our preferences, which are shown superficial if being bad at them is our grounds for casting them away.  After all, are we not like the fox, that declared the grapes sour, purely because we could not reach them?  In a way, this may be true, but a reality is that in this world, skills are not necessarily their own reward, and imagining that they are is to neglect the realities of our universe in lieu of something all too idealistic, rarefied, and divorced from both the world and the way […]

It’s My Fault

When I think about life and all the things that I want to accomplish, I realize that there are many barriers that hold me back. No matter how I look at myself and everything in between, there’s an inescapable reality that comes to mind: “Somehow or another, if I look at any part of what I see, I can conclude it is probably my fault.” Whether this is true or not, it’s the feeling that I carry into life. If I didn’t do something, then I think it is my fault. If I did do something and it went wrong, it is also my fault. Almost everything that happens in this lifetime and to me is my fault. It’s a strange, liberating but also potentially harsh way of looking at the world – this idea that somehow or another you are responsible for everything that you experience. Trivially, this cannot be true for the simple reason that external affairs and things aren’t totally in control, But it’s definitely a liberating one. Like you, I am just another human being. I might have talked to certain people that you may find difficult to reach. I may do things that you may not expect, or otherwise consider conventional. But like you, I am human and in many ways I am weak. Across countless occasions, I can remember the ways I planned but did not execute, seek after things but did not cross the boundary as mistakes stretch out across time in the proof of time gone by, but things not done. I look at all of that and I accept it. This is all very different from what I experienced when I was a younger person. The idea of failure was unacceptable, and I would do everything in my power to fight against it. Now I’ve come to realize that the world is […]

Mensa – A Small Reflection

Today I thought I’d write a brief blog post on Mensa, the organisation that I’ve been a part of for the past couple of years. It’s been a long time since I really thought about this, but a lot of things have really changed.  As Carl Jung once said, “We are a psychic process which we do not control, or only partly direct. Consequently, we cannot have any final judgment about ourselves or our lives. If we had, we would know everything–but at most that is only a pretense. At bottom we never know how it has all come about. The story of a life begins somewhere, at someparticular point we happen to remember; and even then it was already highly complex. We do not know how life is going to turnout. Therefore the story has no beginning, and the end can only bevaguely hinted at. The life of man is a dubious experiment. It is a tremendous phenomenon only in numerical terms. Individually, it is so fleeting, so insufficient, that it is literally a miracle that anything can exist and develop at all. I was impressed by that fact long ago, as a youngmedical student, and it seemed to me miraculous that I should not have been prematurely annihilated.” I joined Mensa when I was a teenager of 17. Insecure, lacking identity, and wanting to try something new.  Imagine my joy then when I took the test scored a pretty decent score and ended up joining the Society, finding it to be a safe harbor for myself in a strange world. I thought it was a natural thing to do – to find myself a spot where somehow I wouldn’t feel so alone, to be in the presence of people who were the brightest in the world, who could change that world and make it a better place. There you […]

The Future of Writing: How Automated Speech Recognition Will Transform Your Writing

In the modern world, creating documents is a fundamental part of almost every profession, and they are key to a variety of tasks: communicating ideas, formalizing agreements, sharing information, reporting progress, instructing, or preserving records. Whether you’re working in business, education, healthcare, law, or creative fields, the need to produce written content is pretty much everywhere — whether you’re creating a PowerPoint deck, writing a report, or crafting a script either for a YouTube video or for an episode of a TV show, you’ll definitely have to sit down and begin writing to bring out your ideas. But as you may know, writing isn’t always easy. In fact, it can be tedious and painstaking, imposing challenges upon your body that are difficult to deal with, such as carpal tunnel syndrome and the stresses of sitting down for long periods of time. Thankfully, it’s a challenge that has a solution: Automated Speech Recognition (ASR). ASR is a technology that historically hasn’t been the best at reporting down what people say, but it has remarkably improved although the best of it is something that still evades the modern and widely available voice assistants on iPhones and Android phones. However, nowadays apps like Wispr Flow and also MacWhisper work effectively and allow dramatically more accurate and longer transcriptions that serve niches such as creating subtitles, as can the ChatGPT app on your phone along the way, which you can download on iOS or Android, Which allows you to use your voice to interact with your devices in ways that have historically not been possible and that also transform the way that we use our technology and therefore interact with the world. Let’s dive into why. While some of you already know that I started using Wispr Flow recently, I’ve actually been using a range of different transcription tools as part of the suite of different apps that make life simple and […]

Wispr Flow: The Future of Voice-Activated AI Transcription

In the past couple of decades of human history, I can remember the seminal inventions that shaped our human existence so profoundly that somehow or another, whether we realized it or not, our lives had changed. Of these inventions, the most immediate that I can point to is Google, the search engine that made it so we could see the entire world. Beyond that, I’d say Facebook, the social media app that connected the world in a strange technological network.  The next one of these and probably freshest in people’s memories is ChatGPT, the tool that showed us the power and usefulness of generative AI, highlighting for us both the revolution of this new technology and also heightening our fears that one day robots would take over all of us. Well, I firmly believe that the next one is here, and its name is Wispr Flow. Download it here!  But what exactly is Wispr, and why are you asking me to download this?  Well, I’m glad you asked. What is Wispr? Wispr is an AI transcription software, but it is not just any transcription software. It’s a transcription software that activates at the touch of a button.  You can use it in any text field and begin transcribing what you are saying by nothing more than a touch of a button and then speaking into your microphone, which ends up creating transcriptions like this, and even intelligently paragraph what you are saying while at the same time minimizing redundancy by fixing mistakes for you on the fly, based on your writing style, yielding transcriptions like this. What does it cost? The software itself is free to use for up to 2,000 words in the course of a single week if you choose to use the Flow Basic plan.  On the other hand, if you use Flow Pro, which most of you probably will. […]

Meeting Tun Dr Mahathir

Today I had a conversation with Tun Dr Mahathir.  This is the kind of conversation that a person doesn’t normally have. I don’t expect that many people will have it or many people would have had it. Given everything that has happened so far, it’s far from clear that many other people will be able to have it, and so I know that it is a rare and wonderful privilege.  I remember clearly all the things that happened. I showed up in a GrabCar to the Perdana Leadership Foundation, ten minutes before our 9:30 appointment.  Walking in to the picturesque building, there I saw our very first national car in blue – the Saga, brought forth from one of Tun Mahathir’s pet projects.  As I looked around, I saw that the place was grand – the paintings of prime ministers depicting Tunku Abdul Rahman, Tun Razak, Tun Hussein Onn, Tun Mahathir, and Tun Abdullah – the gallery – the chandeliers and carpeted floors broken only by gorgeous wooden balustrades that led a curved staircase up into an open space. I stood there spellbound – I had not expected a place of such beauty.  As I looked around, I realized that I had arrived early and it was not time for my appointment yet. But before long, my contact Adam called – and so with bated breath, I walked into the room where I would meet Tun Dr. Mahathir.  In the morning, I had watched Khairy Jamaluddin and Shahril Hamdan’s interview of Tun Mahathir on 2X, paying attention to the questions that he had asked and all of the things along the way, which was also interesting because incidentally I’d also met both of them just the other day at a book launch featuring Kishore Mahbubani – How strange fate is and how the world seems to connect everybody in short order.  […]