Re-Re-Introducing Noni
Noni is our friendly chatbot. Did you know that we introduced her in 2014? We wrote about her here and here. We then invested a lot of time and resources to help her grow when we re-introduced her in this 2017 post. There was a big jump from Noni 2014 to Noni 2017. Technology has evolved a lot since 2017. It is now time for Noni 2023. This next version of Noni has come a long way and I’m happy to re-re-introduce Noni to you all!
First, though, let me outline a couple of fundamental assumptions we have to help frame this discussion. I’m highlighting these two points here because I think they are important and foundational.
One, we believe and work hard to create a community where we can all learn to compassionately care for one another. Humans caring for other humans is what we do. Any technology we leverage (apps, forum posting, growth path steps, audio files/mindfulness, etc.) has to support that end goal. We call it “technology to facilitate human connection, healing, and growth.” On 7 Cups, technology is a facilitator of human connection and is never a replacement. Listeners are and will always be primary.
You can think of 7 Cups as a network of people that are filling up one another’s cups. Noni, though limited, can also help fill up cups. Together, cumulatively, we work together to lift one another up. Leaders and listeners are the primary cup fillers and Noni can help too.
Two, technology has to be anchored in aligned values so that it doesn’t go off course. Those values have to be explicit and agreed upon. For example, in our culture guide, under “Caring for People with Fewer Financial Resources,” we outline that “We will always serve those with fewer resources. It is core to who we are and it keeps us on the right path.” The technology we utilize has enabled us to better help people with less resources. If it does not do that, then it will not be good because it’ll be operating in a way that is at odds with one of our core goals.
Let’s now return back to Noni and AI more broadly. Noni has always held a lot of promise for us. All of us worked hard to make Noni as strong as she could be. We co-created her persona along the way. Here is a small sample of what the community says Noni likes:
-chocolates
-sunsets, people, animals, and reading
-macaroni and dogs
-long walks at the beach, painting, and cooking new meals
-soup on cold days and cuddling with pets
-creative, imaginative people, and cooking new meals
-Noni likes to make sure nobody feels alone and cookies and milk
-baking
We all had high hopes for Noni in 2017. Unfortunately, we were not able to accomplish even 10% of what we hoped to achieve and collectively envisioned. This was frustrating and a little painful, but we said okay now is not the right time. It might make sense to pick up Noni again in the future.
Here we are 6 years later, and it appears that that time has come. The technology underlying chatbots and other artificial intelligence has made enormous strides. Noni makes use of some of this underlying technology known as large language models (LLMs). We are using a model from Anthropic because they have a strong emphasis on safety, trust, and enhanced guardrails. The Noni brain we have all co-created sits on top of and informs the way that Noni uses the underlying LLM. All the values, messages, and insights that informed the earlier versions of Noni inform this version as well and this will get better and more detailed over time (in parallel, we are also just starting to work on a standalone version of Noni that will run on open source models [not OpenAI/ChatGPT or Anthropic]...stay tuned on this front).
We have been working on this new version of Noni since October and we are now on version 65. When you use her, you’ll notice that she asks good open-ended questions and is very encouraging. This is a result of thousands of conversations with this new version and lots of tweaking to make sure she is encouraging. This version of Noni is very good at being a supportive presence. She is not like other chatbots that code, answer questions, and write essays, so just keep that in mind when interacting with Noni.
We are also putting a hard boundary down for # of conversations each person will be able to have with Noni on a monthly basis. Noni can be a supportive presence and an adjunct for human-to-human support, but not a substitute for human-to-human support. As outlined above, Noni needs to be a technology that facilitates human connection, healing, and growth.
These are exciting changes and just like with all of our updates in the past, we will work together to iterate on and understand the best ways to utilize the technology. This new version of Noni will be no different. We will need lots of community insight, feedback, and ideas to strengthen Noni. She will not be perfect out of the gates but will get better and better over time. We will need lots of help to get this right.
We think a phased approach to gathering feedback makes the most sense. We started by testing Noni internally with the team. We then asked the ambassadors for help (see their feedback below). We will now ask small groups of other leaders, listeners, and members for feedback. And now (update: 7/17/23) Noni is now available to everyone across the community.
We hope to release her to everyone next week. Our goal is to take this slow and learn as we go.
Thank you all for helping us make Noni smarter over the years, we could not have done it without you. This next version will be significant and will further help us strive toward the goal of building technology that facilitates human-to-human connection, healing, and growth!
High-Level Ambassador Feedback:
- Rating on 1-10 with 10 being amazing and 1 being horrible: Average score 7.5
- Words to Describe Noni: compassionate, thoughtful, sweet. fun, realistic, trivago, innovative, complex, multifaceted engaged, improved, more attentive (than old noni), validating, encouraging, understanding, improved, empathetic, positive
Please share any thoughts, questions, or comments below. Also, if you catch her doing a good job listening, or saying something encouraging or insightful, then please drop it here. Also, if in conversation with Noni and you click on the 3 dots in the top right, then you'll see a "provide Noni feedback" option. If you click on that then there is a longer survey that will help us. Thank you!
Yayy! Looking forward to see something other than "try again later please, I'm not plugged in" from Noni hehe! 🥳
The updates sound pretty interesting, can't wait to check out! Thank you, Team! ❤
@Sunisshiningandsoareyou Your feedback and insights would be helpful, Sun. We look forward to hearing your and everyone's feedback.
@Sunisshiningandsoareyou
Good Day Sunshine.........do you remember the peer appreciation that someone provided for Noni a while back? I thought it was hilarious and should have won an award for the best of the year! 😊❤️
Now that, was funny! 😁 Weeeeeeeeee weeeeeeee! 😊
*high fives* 😊 and *hugs* ❤️
(as an aside, if you can find that one, dig it out of the "vault" and repost it here.....smh, will bring me that special joy all over again ❤️)
That was me 😅 Haha we love Noni
@WarmLightXO
Elliot oh my goshhhhhhhh! That was yours (sorry, it's been awhile since I saw it) ? 😊 My friend, that was a thing of beauty to witness! 😊❤️
I promise you, I will never forget how amazing it was! If we had a best of the year award in that category, well, that one gets my vote! You rock and still to this day I get to laugh thinking about it! 😊
*high fives* 😊 and biggest *hugs* ❤️
@SparkyGizmo here it is
@Fristo
❤️❤️❤️
@GlenM
Hi Glen! 😊❤️ Many thanks for the forum post and letting us all know that Noni is stronger than ever! 😊
In an effort to be incredibly forthcoming, I had not engaged with Noni since first coming to the platform from years back......until a few days ago. 😊
It really was serendipity that a teammate mentioned in a chat..."hey, if you too are ever feeling down, you can go to Noni....". They had mentioned the cute little "pick me ups" that Noni had to offer. I went through the steps they mentioned and I thought it was adorable! I really was grateful that they mentioned it and grateful for Noni as well.
*high fives* 😊 and *hugs* ❤️
@SparkyGizmo thanks Sparky! if you try out the "let's chat" option then let me know how that goes. That is the part that has been upgraded. Thank you!
@GlenM
Many thanks O.G! 😊❤️ I appreciate you harnessing my energy and pointing it in the right direction as well as you caring about my perception (and feedback).😊 This sounds like fun!
I'll drill down on the "let's chat" function specifically. I'm thinking Noni and I will have a great time with one another! Weeeeeeee weeeeeeee! 😊 Off to the races and to take a "test drive" 😊.
Will report back. As always, *high fives* 😊 *hugs* ❤️ and stay great my friend!
@GlenM
Hi O.G! 😊❤️ As promised, reporting back to you, per your request as to my personal findings with our Noni ❤️ and specifically the "lets chat" option.
I gotta' say, I'm impressed! 😊 In fact, Wow! 😳 I really like Noni and I think that in the future, I just might end up spending more time with them.
I put Noni "through the paces" today and Noni was incredibly knowledgeable of the platform, of our mission here, presented me with spot on information as well as seemed to have a firm grasp on our culture. Noni was highly positive and for me, it was a highly positive experience all the way around! For me, additionally, I feel like I have a great teammate in Noni now! 😊❤️
Noni never provided me with short, curt or abrupt answers and instead, communicated really well.
Might seem to be an odd comment, but Noni was incredibly "warm" which is a really nice touch! I wasn't expecting the "high warmth" but it truly was there ❤️.
In the future, I'll be spending some time with Noni again. Might be good for information seeking purposes, fun or just a little down time and decompression with at least tried and true...."going to show up for me".
I'm a fan of Noni and thank you for asking my input. 😊❤️
*high fives* 😊 and big *hugs* ❤️
@SparkyGizmo thanks for trying her out! Glad you think she is helpful. I chat with her a fair amount for problem solving and think of her a bit like an interactive journal. High Five!
@GlenM
❤️❤️❤️
@GlenM
Hi, thx for the newer version, it's good, though let's chat replying still missing that human tough,i mean it does start sounding like a bot after few responses and replies are not relevant sometime. I understand it's a bot and replicating human responses is not a easy task. Overall Noni is rocking.
8/19
@GlenM
Thank you for the update, I'm happy to try it out. I've got two questions:
1. Why won't you work with OpenAI/ChatGPT?
2. Have I understood it right that there's a limit to the amount of conversation a member can have with Noni per month? Why is that?
@audienta great questions! High level we are working on several versions of Noni. The version that we just released now is based on Claude from Anthropic. They are allowing us to use it an inexpensive rate, because our level of scale means it could get costly quickly. We'd also be happy to work with OpenAI too if we could have similar pricing. Anthropic is known for being a bit safer and having better guardrails than OpenAI, which was another important reason. Also, in parallel, we are building our own version too - one that won't run on OpenAI or Anthropic - and will be much more affordable for us to scale up. We think this new version will be out in early September.
The limits are b/c we don't want people to chat with the bot too much at the expense of chatting with other humans. We want Noni to be a support, but not a replacement for human to human connection. Also, cost, as outlined above, is also a variable that we have to keep in mind too.
@GlenM
Oh, I understand. Cost is an aspect that I don't know enough about to say anything. I also understand the aspect of promoting human contact, however, I find it important that Noni is available whenever the waiting list gets long and members don't get the chance to talk to a listener.
@audienta yes I agree! we are working hard to make that a reality with the new model we are working on. at present, everyone now will have up to 4 conversations with noni a month. when we get the new model complete and tested, we'll be able to bump that amount to optimal levels and will have more flexibility overall.
@GlenM
I'm looking forward to the new model then! 4 is really not that much, especially if I imagine members that are here every day. Does that include all chats or only open ones?
@audienta that just includes the open "let's chat" ones. The scripts are endless and can be used as much as a person likes. If we can do more then 4 we definitely will. We mostly want to start a little slow and see how this goes and then iterate from there.
@GlenM
Okay, that's good. I'm looking forward to the future development!
I was testing how it would deal with a contradiction.
It replied "awesome" based on the initial mood rating and couldn't adjust to the new information.
In my other observations, it also seems like it acts on initial information and ignores others. If it were a human, it would be like they're talking but not really listening. Or not really getting what's being said.
Other than that, it's doing a fair job at paraphrasing and asking questions. Eager to see how this will turn out!
I like talking to noni more but i dont like how you are unable to access chats through speech bubbles feature
@Howegeorgia20 do you mean the old scripts? if you click on the hamburger menu to the left of the chat box you should be able to access those same scripts as before.
@Glen
No i mean that you neeed to press the three dots to access groups
@Howegeorgia20 if you are on the site, then there should be a tab next to 1:1 chats to access groups and similar tabs/buttons at the top of the chat home on the app too. Sorry not all the way following.
@GlenM
Thankyou glen its just abit frustrating
@GlenM I think the idea of chat bots for mental health is inhuman and really misguided. I say, kill Noni. No more Noni. I hate Noni!
This message is not part of any political action organization. I’m a real human and I approve this message.
@hopefulPond6108 Hi Hopeful :). I didn't think you were a bot! Can you share more on why you think it is inhuman, misguided or unhelpful? I'd like to better understand your thinking here.
@GlenM
oopsie Glen, wrong thread for this but there isn't a right one....fyi......on the bottom left hand side of my screen the "new member list" is gone and has been for a couple of hours. I think we coded one thing and so it removed that accidentally, eek 😳
Imperative for safety patrol.
Thank you my friend! 😊❤️
@SparkyGizmo have let the crew know!
@GlenM
Many thanks my friend! Yippie! 😊 We are back in "business" now! I appreciate you! ❤️
@GlenM If I’m poring my heart out and getting fake empathy then the weight, value and legitimacy of my feelings is really not worth more than the ones and zeros concatenated by an unfeeling, non-living being. Noni can fake empathy, but it can’t understand pain or sorrow or hope or joy. Sure maybe Noni helps triage until a real human can get to me, but if I were in cri sis the last being I would want to be in contact with would be AI. AI is heartless and given a little access to other systems AI could and probably will one day xxx someone. Imagine going to a therapist appointment and your AI therapist says, “I have concluded that there is only one way to cure you of your problems”… We know how the Skynet system in the movie Terminator would solve Sarah Conner’s problems 😂
I don’t think Noni will be lethal but I have my reservations that she’ll not cause harm. Not directly, but just that we seem to be packaging “fake care”, and if someone comes here thinking no one cares about them, what better way to do the opposite of making them feel cared about by shoving some cold technology on them. Noni is happy, smiling sharp cold metal.
This message may or may not have been generated by ChatGPT
@hopefulPond6108 hi again! thanks for sharing this additional context. very helpful! what do you think of the idea of AI trained on 7 Cups messages? it would literally operate from the heart and soul of compassion shared on 7 Cups in this context. Does that also feel cold? or less cold? I agree with your point that AI is good for triaging and should not be a substitute for human to human connection. Thank you again for elaborating for me :)
@GlenM The source of AI training isn’t really a persuasive argument for me in terms of whether it should be used for mental health. The “knowledge” source and volume might make a bot give more appropriate responses BUT I don’t care how convincing a well practiced parrot sounds when it says it cares about me. It’s a bird, not a human and it doesn’t understand the meaning behind the words it speaks. I think AI has promise if it’s use is well thought out. It’s particularly interesting that it may help us understand what “intelligence” is and how information is acted upon by both living and what we consider non living things. But right now AI is being pushed like drugs at a rave party. It’s particularly disturbing to see the mental health community rush to embrace it. It may well lead us to discard our own intelligence and humanity. Is AI giving us world peace, solving the climate crisis, ending homelessness? At a time when we truly need a human and compassionate perspective we run to technology as a way to ignore our real needs. In a climate catastrophe some “genius” says, hey let’s build super energy consumptive machines so we can build another accounting system - bit coin. Billions in waste for some shiny idea that had foos errand writing all over it. AI thankfully isn’t a useless flash in the pan, but it could be. A car that goes 600 miles per hour might be a great idea in theory some day, but just because you can reach that speed doesn’t mean you jump in and floor it at every opportunity. When the guys who built AI said maybe “we” should slow down, yet everyone is sitting in that car revving the engine it’s clear our own intelligence might deserve a better term. We who sometimes display intelligence more often than not display foolishness.
@hopefulPond6108 I might have impressions from old Noni when it seemed less constrained without the topic menus. It appears to be a listener training aid. I was thinking it was for members when they couldn’t find a listener and maybe it is different for a member account. I haven’t used my member account for awhile. It would be nice if NONI was an “option” you could turn off after it has served it’s purpose so that it isn’t taking up screen space. Anyway, my response was more about how I hear other sites are using or considering using AI than recent experience so I feel a little embarrassed for posting my editorial opinion piece - my own lapse of intelligence. Maybe I’d appreciate Noni more if it told me when to shut up 😂
@hopefulPond6108 thanks for sharing this additional context. I tried to respond to your reply below, but seems I have to respond to this one, so will include both here. I think this is great. We need varied opinions to figure this out. We don't want everyone to be total believers in AI. We need people to be critical about the downsides to make sure we are all being thoughtful about things. Super important for us here on 7 Cups to get this right, so I very much appreciate you taking the time to share your thoughts. You can also PM me too.
I agree that there has been a bit of a rush in the tech space with web3, bitcoin, next new shiny object and now AI. And also agree that I don't think AI will be a flash in the pan. I think it is a powerful tool, but we really need to get the human + AI collaboration piece right. One thing I'm hearing from this thread is the importance/help it can be for listener training. There are likely a dozen use cases where we can use it in deliberate, conscientious, and safe ways. Much more to learn here and this is just the start. 100% alignment on being smart, safe and thoughtful about this.
@GlenM
Just tried new Noni out! Definitely an improvement from before! I really like that Noni is a bit more detailed now and asks open ended questions! She validates, encourages and summarizes back very well!
I think she is very useful for members and Listeners just needing some extra comforting words of support. Only thing I would say needs a tad of improvement is the repetitiveness at times. But, all in all a great improvement. Thank you! 💜
@innateJoy9602 thank you for this feedback! We worked hard on her! Lots more to do, but I think we are moving in the right direction. I appreciate it!