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

Inevitable Hash Brown

In the journey of life, change is inevitable and I say that unironically. Why “unironically”? Because people have repeated “change is inevitable” to high heaven and it often comes off like a word hash brown, fresh off the shelf of a cooling rack; toasty, delicious, yet ultimately unhealthy, factually fast food language. Yet so as the hash brown is delicious, so is the language of ‘change is inevitable’, only to be appreciated if it is savored properly. If it seems a little strange to you that I’m writing about hash browns and change, know that it is for me too, but it is one of those changes I see from 2025 – the sort that involves taking on random streams of thought and fashioning them into the rivulets that add into a current that move forward, summing into a flow. I do wonder a little bit about whether there’s a consistent pattern though. I find that I’ve become a bit more thoughtful about things like these – that I have a higher discernment for what constitutes quality thoughts, while at the same time holding the small blessing of being able to evaluate things in light of a larger goal of social change and transformation through the development of content, ideas, and otherwise. It sometimes feels like I am in the middle of a grand dialectic with the world, one where I stand in the marginal territories of an evanescent frontier, fighting against a world that I do not want to come to pass, aiming to reshape it to my will. I think about so many things. Biology, willpower, society. Mind, hand, money. Power, politics, philosophy. Birth, life, age, death; competition, progress, history; nation, spirituality, world; destiny, history, legacy. It seems to me that these words now come out easily from me, not from the outer rim of the deeper examined mind, […]

Influencer

In Mensa events, one annoying character (generally ok person but annoying with an emphasis on the G) sometimes comes up to me and starts talking about my ‘influencer’ career and how I’m ‘influencing’ people in a presumptuous fashion, acting as if suddenly he is the be all and end all of ‘influence’. Well, he is not and he is lovably mediocre as far as I know so I’m not too concerned about that, but I think it’s certainly an interesting concept to explore. The concept of an ‘influencer’ is so interesting. In purely technical terms, an influencer influences, and the derivational morphology is inescapable; to be an influencer, you must surely influence. But the question naturally arises: What kind of influence do we mean here? After all, there are so many kinds, which the world almost invariably collapses into a few different and well defined stereotypes. The comedic genius who specializes in fun, short, but stupid skits? The dancing girl thirst trap using every single part of her body to try to get you to click the ‘follow’ button and oh by the way buy some lipstick with a 10% discount code and 15% commission? The travel blogger cum exercise guru here to teach you the vastness of Borobudur on a diet of tempeh and budu budu? There are so many kinds out there, all valid and all cool in their own way – the internet is a wonderful place with lots of incredible and talented people, after all, here to persuade you and to make their fortunes in ways inconceivable at the dawn of humanity and even now to members of an older generation who cannot deal with that idea in any way except to infantilize or look down upon it. To be fair, it is not entirely the older generation’s fault that they think that way, because many such […]

“Nice Guy”

Many people in this world consider themselves what we call ‘nice guys’. I do not. I may have tried to convey myself as a nice guy at an earlier point, to act as if I happen to be a nice guy, to think about ‘what other people think’ to the point of neurosis… But I would not really consider myself a nice guy. What this DOESN’T mean is that I go around attacking people needlessly or getting into fights I don’t need to get into, fight against my actual interests – rage against the machine like a two bit two hundred kilogram behemoth of a manchild on a warpath to destroy the known and seen universe. But what this DOES mean, is that I will express what I think without fear, without favor, without the sense that “OOPS SOMEONE’S OUT TO GET ME” because if I see a dude who needs to get scolded, I am going to scold that dude, think about how to more efficiently scold the dude, and even think about how I’m going to use people to further my own goals. If that sounds bad, it probably is – but that’s just another aspect of me – I have certain goals in this universe that can only be attained through changing the ways that people think, believe, and ideate in this world on small and large scales… Which means I cannot ever avoid conflict. …But that’s just as well though? Conflict is how stories move forward. Conflict is how main characters turn from unknown troglodytes in the gonadic expression of a whelp into world changers, the hero in the demon king story. If a nice guy ceases to be a nice guy the moment he goes out there and starts fighting with people, then it is clear: I am most certainly not one of those ‘nice guys’. […]

A Small Speech on Articulation

Today, I want to talk about articulation. It’s a word that’s used a lot in the English language in many different contexts, all of which are dear to me. In music, it’s used to describe the way someone plays an instrument. On the cello, it is how the bow glides, pressure is applied, and weight is distributed in accordance with the needs of the music. In a pure linguistic and sound sense, it is how air interacts with the tongue, mouth, and vocal cords to produce sound. In the parlance of the English language, it is how one communicates one’s ideas, structures them, and brings them out from the depths of thought into the seen world, where they will influence others. I think articulation is a deeply incredible skill. Throughout history, the greatest articulators have never been able to articulate. The greatest articulators have been the most successful political leaders, the most influential statesmen, the finest executives of their era—merely by playing on the power of phrases that their minds constructed, in turn pulling out the feelings of entire generations, summoning them to the causes of the speakers in every instance. And it is no wonder that speech and language are rich and wonderful, yet they are only minute and poor representations of our deep inner thoughts. Used in the wrong way and in an unfocused manner, words will only inspire vagueness, boredom, and the mere hints of attention before the listener falls asleep. Summoned rightly, though, and they, in turn, will inspire from the still depths the uproarious fountain of joy, sadness, hatred, and love in every which direction. As the heart is activated and the mind primed for more, you say that these are forces that seem outside the scope of an English class. They are not things to be concerned with or trifled with. How can mere words, […]

Winds of Change

To almost anyone who knows anything about me, it might seem strange that I’m taking such an interest in politics recently – I transitioned so suddenly from Pathways To Excellence to suddenly talking about so many different controversial topics and ideas that somehow your feed is now filled with a range of YouTube videos that hopefully are a little bit legible. I get it – you feel like I’ve changed as a person. You know what? I probably have – but maybe not in the way that you might have expected. I think I was always interested in politics, for one thing, and that somehow meeting the smartest people of my generation and of the next generation was the way that I managed to allay my discomfort with Malaysia – a systematically broken, thoroughly divided society when you look at it beyond the enclaves and the confines of everyday reality; it was somehow easier to fill up the hole in my heart whenever I thought about this place and how I had my lot connected to it with the feeling that somehow, even if the place were to be a dumpster fire, at least we had all of these talented people. But soon, this bandaid, had to be taken off, as all bandaids eventually have to be – and so it was, as I faced reality, with a single and enduring rip. At some point, I realized that talent on an individual level is not the solution to this country’s problems, and moreover that it is not necessary for me to solve them – but only to play to my internal conscience. It was I think at that point I saw Malaysia for what it really was, and what I would create from then on out.

What I Would Do Differently From The Madani Government (In Managing Speech Online)

As some of you may know, I have recently been making a range of videos about topics that I think are important for Malaysia to discuss, namely the 3 R’s. Recently, the user ​⁠@coldsunflares asked me on my YouTube channel and my video about the penunggang agama Rayyan Wong who recently accused PMX and our Agong of eating in a non-halal restaurant about what I would do differently from the Madani Government when it comes to regulating what some may call extremism or penunggang agama.  It was quite a thoughtful comment, and I reproduce it here.  “You mentioned the government’s inability to deal with these kinds of issues, which for the most part, is true. However, how would you propose they deal with it? Because any time the government decides to take these so-called “decisive action”, they are labelled as “draconian, stifling freedom of speech” among other things. On one hand, the government is hard pressed to take these measure because of their history of championing reforms, equality and civil liberty, but on the other are those “from the other side” who hides behind the guise of freedom of speech (without decorum) to spread malicious statements, as is evident from multiple recent incidents, i.e. China flag issue, mandatory Halal cert, etc. We are bursting at the seams with people who point out the problem, but not so much people who can come up with a feasible solution to these issues.” The comment I wrote was too long for the margins of the comment window, and after I had written it I realized – it was too long even for the YouTube post window, so here it is in full blog entry glory.  Response begins:  I think even now, the Madani government is having huge problems with actually portraying itself as a compassionate government – but I feel that this is because […]