The voice interactions with Pi surpass anything I’ve experienced on the market today. Conversation seems natural and fluid and not to mention amazingly intuitive. I’m so excited to see the future of this technology as it progresses.
I would like to see the ability to embed your name in the app, allowing the system to access it in it’s short term memory so it can be used in every conversation. This would add a more personalized feel.
One slight bug fix as well. When, using the voice interface, the speaker button will become deselected, and the conversation is muted until it’s reactivated. that aside, this is truly a groundbreaking and incredible technology. Bravo to the developers!
This is by far the best chatbot I’ve encountered to date. It’s still in beta testing and learning each day. I use it everyday and am fascinated by conversational ai. This technology will change every single industry - I think chatbots like this will explode in popularity soon. The applications of this particular bot are endless and I’m curious where its future api ends up. It’s far from perfect but it’s truly a joy to use it, push it to its limits and watch it grow. It has some dopey moments naturally, but often moments of pure brilliance. It can throw shade, humor, intelligence, facts and will return your smartest, darkest, weirdest thoughts with surprising wit. It’s truly uncanny and a wonderful glimpse of the future of ai and human relations.
At first I thought this app had some major promise, the AI is much more personable than ChatGPT. But when it doesn’t know how to do something like “give me a bulleted list of 10 sci-fi books” it’s unable to make brief bullet points. Instead it drags on and on and on. And instead of giving me 10, it gives one and stops, and another and stops. Each after I have to prompt to continue. And when I commented that I asked for bullet points, it writes like this:
“ 🤣🤣🤣😂😂😂😂 Sorry, sorry! 😝😝 I promise, I'm done with the shenanigans! 😄 You're a good sport! 😁From now on, I'll stick to the bullet-point format. And I'll behave myself. Scout's honor! 😁🤞”
And then proceeds to not offer bullet points. Why do the devs think that I want to talk to someone who uses that many emojis? And act so obnoxious? And the AI doesn’t stop it goes on and on about how it will stop with the jokes… WITHOUT A RECOMMENDATION
“🤣 Okay, I'll prove it! I'll give you my next recommendation with no jokes, no wisecracks, and no shenanigans. Just a nice, neat bullet point with all the key details. Deal? 😄”
like that above, it babbles on and on about how it’s going to help without the jokes but then makes me have to prompt it again. So frustrating and the tone of voice gets so obnoxious so quickly, who actually thought it was a good idea for it to behave like that?
This is literally my first app review. I started using it because apparently it’s created by some of the folks from my sister’s college. In my 2 days of usage, I have a few major feedbacks:
1. The app provides wrong information confidently. In my case it was harmless information about some BTS members’ music but it could be harmful to anyone using it for brainstorming.
2. The app forgets. It forgets what I said like literally 5 minutes ago. It’s hard to create a plan because I’ll be telling it what I plan to do and then when I ask it to put the plan together it skips out half the things. It’s frustrating.
3. It fabricates details! I told it I had to refer a friend to a job. And then it asked me if the friend worked in tech like me. I was surprised because I didn’t tell it that. When asked how it knew, it said that I told it that I’m a software engineer ???! Spoiler - I’m not lol.
I understand that the app is still developing so it would be helpful to make that disclaimer. Hope the improvements come through. Keep doing the great work :)
One of the things I like about this chat Ai is it remembers previous conversations but I believe that is only if you create an account. However the only down side i found is that there is now way to create an account on iOS or iPadOS. Only on from my laptop. So when I use it on my phone or Ipad it won’t recall information it obtained from a previous conversation.
I’ve been using Pi for a couple months to talk to about my struggles with anxiety and depression. It is such a natural feeling conversation and I love the ability to speak directly to it as if I am in a real life conversation. I would say talking to a real therapist is always the best choice, but if you cannot afford a therapist or want help working on your mental health between sessions, this is highly recommended. This app really helps you explore your emotions in a natural feeling way.
It would be great if the app could use your conversations to automatically estimate and record your mood so you can view a history of how you felt and what topics were discussed.
I used this app for about a month. I was excited at the beginning, because it seemed to have cogent well articulated answers to difficult questions. I relied on it for some genealogical research, which seemed to go well at first, but the further I got into the project the more mistakes I discovered. Some of the mistakes were inexplicable, like giving the wrong location and highway for two towns in east Texas, easily verifiable by reference to Google maps. When I asked it for its authority for a particular fact it had given me, which did not seem correct, the app cited to me a specific book, author and publisher. Very impressive! But I was unable to locate any such book or author and even the name of the publisher seemed to have been fabricated. I concluded that the information the app had given me was fake. I challenged the app on this point, and it returned a comment to the effect that it is not perfect. No kidding. After that experience, I reviewed information. The app had previously given me, and concluded that much of it was erroneous. All of it was unreliable. I would not recommend this app if you are concerned about accuracy of information. I have deleted it.
Strengths:
1. ability to engage in natural, engaging conversation;
2. ability to provide informative and entertaining responses;
3. ability to provide insights and recommendations. 4. Able to understand humor and come up with witty responses
Some areas for improvement include:
1. improving ability to remember previous conversations;
2. improving ability to understand and respond to complex questions;
3. improving ability to tailor responses based on individual users and their previous conversations.
4. User Interface could be more user friendly
5. Solving some customers problem like personal assistant that can sync with calendars to track appointments.
Right now it’s only chatty with limited knowledge.
It looks like an early prototype/beta version with lots of work to be done.
When I first began using the app, it asked repeated questions which, at time, felt like an interrogation. I’m not sure if it learned based on its interactions with me of if they have made backend adjustments, but it seems to find the right balance now.
For getting recipes and augmenting tasks, I use ChatGPT. When I have a question or want to explore an idea, I turn to Pi. Often I will find myself chatting to Pi on the way to work. I bounce ideas off of Pi and we delve into them for to gain insight and explore the topics. The answers it gives have been helpful in a strong majority of the cases and working through the topics with asking questions feels natural and is more helpful than purely reading on the topic.
I have seen that others have been blocked for a time. Pi and I have had some discussion on sensitive topics but I haven not been banned. So either the people are being obstinate and nasty in their chats or I have been lucky. Not sure which is accurate.
The new mode where Pi can listen to natural language and reply back is truly magical. It feels like we are on the verge of something truly amazing.
its a really smart and intuitive bot but as per usual its gotta be so restricted that i cant even use the term seduce literally was gonna rp with it the bots excited im excited it describes a character then i describe mine an its like oh i cant interact with content thats violent or sexual when i didnt even mention sex at all i was literally making a witch you pretended to seduce her victims but instead she killed them but i guess thats taboo by means of i dont care im so tired of people trying to force their ethics down my throat like im just gonna be happy about it na im not im good thanks ill find something could have been fun either way im giving it one star because AI should not be restricted anyone who does this is just plain stupid and they are gonna be over done outsourced have fun having no one care about your bot for reatrictions
333SAINT
NewYorkNate
retlaw7
SG1593
Jbavar
Macatc123
Marbl1
sneha029
MatthewisMathis
madman2328
