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 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.  […]

The Night Before I Met Mahathir

It is the night before I meet Dr. Mahathir. For those of you who didn’t know about this, welcome to yet another strange and interesting episode of my life: Tomorrow, I will be interviewing Tun Dr. Mahathir, the 4th and 7th Prime Minister of Malaysia, for my podcast, Pathways To Excellence. I sit here with two books in front of me, the first, The Malay Dilemma, and the next, A Doctor in the House, and I contemplate both and the way they have unquestionably shaped my life. Dr. Mahathir was my Prime Minister when I was just born. From young, I always thought that every country had a Prime Minister; indeed, it is from him that I learned the very concept of Prime Minister itself. For years and years, this had gone on, and I went from thinking that he was the only one who would ever occupy that position, to learning that other countries had ‘presidents’ and ‘kings’, later downgrading the man’s significance as I thought of the ‘world’ and how wide it was, moving first from thinking that Malaysia was everything to thinking that it was tiny, insignificant, hating it, coming back, making it home, and then realising that it was what we made of it. It is fascinating how small the mind of a child is – yet, as I would later realize, how small the mind of an adult is when they fail to contemplate the significance of things that are nearby. I never really thought too extensively what it would mean to actually encounter this person one day. Then one day, many years after my father had died and was buried in the Sungai Petani Christian Cemetery, I found a book. My mum said that she wanted to throw it away, but somehow she didn’t, and there I saw it in its ancient form, yellowed pages […]

Societally Valuable

Every morning I wake up, I ask myself: How do I be someone valuable to society, and how do I create things that are valuable to society? Ever since I was a child, I think that this question has been a part of me – the part that wants to create something that’s of my own in service of the world in which I live through imagination, thought, and the machinations of a mind that will not sit still.  Some may argue that choosing to make a difference is a matter of disposition. I don’t want to give to society. I want to live for myself! Why should I care about what other people think? I consider people entirely able to make such statements and accept that they exist don’t disagree with that – human beings are different and naturally abide in different worlds; bearing different personalities, we approach the world through myriads of different lenses built from different world views, cultural backgrounds, and educational experiences. In such a world, might someone not argue that becoming societally valuable is merely one of many pathways. Surely that is an overgeneralization?  Personally, I feel that that is not so, purely because society is a large and far-ranging concept. Rather than an abstract and faraway entity, it is something that is close and begins from those closest and dearest to us before it extends outwards into the world. Society is fundamentally made up of individuals – our friends, our family members, the people who make up the sum and total matrix of people whom we know and love, and those whom we have yet to know whether near and within our communities, or far away and outside of them. To bring value to these people and by extension to society is not so grandiose as ending climate change, eliminating inner city crime, or resolving […]

AUAM-NAMSA Corporate Pathways Networking Dinner – Some small reflections.

The journey has been pretty interesting in a whole bunch of different ways. Amongst other things, I’ve received a partnership with GerakBudaya, and also in conjunction with the American Universities Alumni Association of Malaysia and the National Assembly of Malaysian Students in the United States of America (NAMSA), we are organizing this event. Here’s the event PDF to showcase that this is quite real. Honestly, even the term Corporate Pathways is a bit of a misnomer. I don’t know how corporate this event is going to be, primarily because it’s mainly going to be focused upon experience sharing and how people thought about their lives in the course of GLC in relation to the education that they received while they were in the U.S. There is a whole backstory to this that goes back about a month or two months or so, but has led me to a place of networking, meeting different people, and establishing friendly chat after friendly chat, rather than transactional moment after transactional moment with a bunch of different people with whom I probably never imagined at the outset that I’d be on casual speaking terms with. Anyway, here are some of the people who will be on the panel. GLC Panel: Nick Khaw, Head of Research at Khazanah and alumnus of Harvard University. Aik Chong Phuah, previous CEO of Petronas Digital and alumnus of the University of Chicago Booth School of Business. Brendan Yap, Senior Executive at the Securities Commission and alumnus of NYU. Athirah Azmi, former Manager, Client Coverage at Maybank Investment Bank and alumna of the University of Chicago  Private Sector Panel: Audrey Ooi, co-founder of Colony Coworking Space and an alumna of Mount Holyoke College, also known as @fourfeetnine. Dato’ Vincent Choo, Founder, Urban Ground Group, Franchisee Subway; alumnus of Eastern Michigan University. Yen Ping Teh, APAC Product Partnerships at Google and an […]