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

Pathways To Excellence

Pathways now has a podcast – please follow it! In the past couple of days, I’ve had the chance to speak to some very, very smart people, and it’s all the result of a weird series of coincidences. Or maybe they’re not really coincidences, and maybe they’re just fate. I don’t know what it is, but either way, I realized that every single member of Harvard’s class of 2028 and Yale’s class of 2028, as well as Stanford’s class of 2028, was watching Pathways to Excellence. Why do I know this? I know this because I ended up speaking to almost every single one of them, only to hear that they were aware of what I was doing, that they had watched the videos, that prepared for their Harvard interviews, or otherwise in some way, shape, or form. It’s also been interesting to watch things play out, as I’ve secured interviews that are very different along the way, with people of rather unique backgrounds, which I’ll perhaps talk more about in the days to come. It’s very inspiring to speak to smart people – I have no idea how that’s going to influence my future just yet, but the outlines are there, but I would have done this regardless of what had happened anyway. What is clear for sure though is that this is meaningful, something I’m honored to be a part of and a journey that I will continue to value in the days to come.

Malaysia’s Harvard Class of 2028

Recently, Malaysia was very fortunate to receive the news that four Malaysians had gotten into Harvard University. Congratulations to Elisa, Victor, Thamini, and Bryan! (And thanks for watching/appearing on Pathways ^^) It’s always fascinating to see the country’s very top talent and the way that they are celebrated in this way, but maybe even more fascinating to become friends with them, which I inadvertently did in different ways. It’s cool that Malaysia can produce people of this caliber of talent for sure – but there’s naturally always going to be a question for each and every one of us: Can it retain them? Honestly, the answer to that question is unclear even for myself. You need to be strong to stay in this country, after all. V.

Random thought

One thing I’d definitely like to do a lot more this year is make myself capable of doing large batches of work all at a time. I don’t mean just going out there and working as hard as possible to put myself through a suffering that is inhuman, impossible to bear through, but instead the simple act of understanding how to schedule things so that you have more time in between the moments when you obtain inspiration such that you have a natural reminder to continue going out there, enter the game, and do as you will do. Willpower of course is a very important thing, but it is limited. That is why we create systems, things that automate our labor, but of course no system can operate without the willpower in the very first place even as it is true that expecting continual, consistent, and unrelenting willpower is a recipe for burnout and self-damage to degrees unreasonable even for the most hardened of men. In this upcoming new year, I look forward to being able to find many more systems that will continue to make work easier for me, to be able to more delicately navigate the balance between willpower effort and also attainment of actual results in the days ahead. I’m given the sense that somehow or another, that needs to be a continual part of everything that I’m doing going forward. How exactly that is going to work out and how it will happen, I am not totally sure just yet, but ideas and intuition abound, and what I’m confident of is that in many ways, this is a knowledge thing. By simply elevating yourself from an initial phase where no knowledge is present to one where awareness has been developed, a person can lift themselves up to heights hitherto unknown. That has been the experience that I’ve […]

Assessing English Standards in Malaysia: An Analysis with the CEFR

Often in Malaysia, people talk about how our standard of English is either sufficiently good that it is the basis of a thesis for investment, or they say that our English is abysmal and needs drastically to be improved – discussions go on and on, and people fight, oftentimes in what seems like a battle for the soul of our society. But what does it mean, actually, that our English is good or our English is bad? Some say that Malaysia aligns itself to international standards in creating its curricula, but others squabble day in and day out, constantly complaining about the quality of English amongst graduates who come into the workforce, observing that many of them lack basic skills that they would expect graduates to have. How can it be possible that Malaysia calibrates itself to international standards while at the same time its graduates languish in terms of their English language proficiency? But at the end of the day, who’s right?  As it turns out, investigating a little further tells us that the answer is both. Here’s where the subject of our blog post for today comes in: The Common European Framework for Reference, otherwise known as the CEFR.  The reason that I’m making this comparison today and telling you about CEFR is that Malaysia uses it to calibrate SPM writing standards.  The CEFR operationalizes language proficiency in accordance with six dimensions, from A1 up until C2. It is an international standard that is utilized by examining bodies across the world in order to designate proficiency levels and descriptors that students attain after courses of study, and it is used also in designing curricula so that students can reach a certain defined standard. Source: https://www.cambridgeenglish.org/Images/126130-cefr-diagram.pdf CEFR operationalizes English proficiency according to numerous level descriptors, providing explanations of what a user of the English language should be able to do […]

On Facing Judgment’s Shadow

Picture this. You’ve written a post that you want to share on social media, or you’ve made a video somehow or another. You’re sitting there on the edge of your chair, just about to click post, but you look at what you’ve written, what you’ve made, you notice that final error, you question yourself, thinking about the manifold ways in which people could be judging you silently and from afar, contemplating in your mind’s eye the dialogues that must be taking place. “Oh my gosh, this person wrote this?” “Oh my gosh. Did he really make that grammatical error?” “Wow, this is boring. Why am I even watching?”“How could he make such a video?” And so the thoughts come out, percolate like coffee through filter paper, and eventually crystallize into little gems of self-doubt, blocking the nervous signal that would have caused you to click. You turn away from your plan, and you declare:”Maybe later, but not now.” Before you know it, the entire project is abandoned. If you’re anything like me, you may have faced this, this feeling of wanting to do something, but realizing, or at least thinking that you weren’t good enough, that the manifold imperfections that existed in you would come out, and that people would judge you one way or another. Well, here’s a fact, though. People certainly will judge you. I mean, how could they not? Everyone encounters something as a first glance, thinks about it, and evaluates it on their own terms. That’s just how it is. The judgment will happen. There is absolutely nothing that you can do about it, and your feeling certainly is right. The thing is though, that even though it is right, this isn’t a valid reason to run away. Because truly, the only way to get past it is to face your fears, to accept judgements as they […]

Work, Life, World.

One of the things I’ve come to really appreciate learning in college is the ability to just work, and work, and work. Sometimes I feel like my work ethic is just unending, and I can continue doing everything that I’m supposed to do, just efficiently and continually, almost like a machine.  I start, I take breaks specifically for the purpose of making sure that my work efficiency is maintained, then I begin again. The cycle continues, and life proceeds just in that way.  It’s one of the miracles that has come about, I think, from being trained in an environment where people were constantly working hard, and a place where people would not just work hard, but also have the right motivation, initiative, and desire for it.  Somehow or another, it influenced me, and rubbed off on me. And before I knew it, I was one of those workaholics out there, just casually pulling long hours without even questioning things, completely by my own volition.  It sounds bad, but I’ve come to appreciate that part of myself quite a bit.  It’s one of the many reasons that I respect myself, and appreciate the person that I’ve become. Because it’s become an enduring facet of my personality, and something that I know that I can look to whenever I think about my identity as a person, but at the same time, I think it’s come with at least two different disadvantages.  The first of these is that when I think about work, I just continue on and on. It takes hold like a vice grip, consuming almost every single aspect of my mind and my thoughts.  The result?  I just carry on doing things in the way that I feel most natural. Ignoring different things, socializing, hanging out, spending time with people, messaging…The list goes on, and I don’t know how many […]