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!
@GlenM Noni is really cool and love the updates but unsure how I feel about Noni saying 'Nice' when I said I was exhausted after my week at work 😂 - it did make me smile though! It would be cool if one day Noni can send uplifting gifs in the chat. But I understand that might be way down the line!
I really love this new version of Noni and you can definitely see how much has changed! Thank you for updating Noni! ☺️
@Raspberrycheesecake love the gifs idea! I'll add it to the list. Thank you for trying her and for the feedback :)
@GlenM yay!! 🎉 No rush for the gifs though - I understand how long it can take to programme and trial things, especially when there are bugs involved with programming! 😅
@GlenM
Hey! Noni has not been removing or editing reminders. You might want to check that out and fix the bug
@tidyHickory3283 we are looking into a fix for this!
@SoulfullyAButterfly
okk!!
@GlenM
OMG you guys finally did it!!!
This is such and amazing step and this will make Noni so much more helpful.
I fiddled around with her a bit and she is really much smarter now.
You can have back-and-forth conversations with her now and she doesn't give you the exact same answer every time.
She can show empathy, validation, encouragement and so much more.
This is such a huge leap from the previous one and I can't wait to see how much she'll grow next time.
A massive thank you to the entire team. You guys are doing such great work so quickly and I can't thank you enough. You guys are the real heroes.
Keep up the good work!
@GlenMI definitely see big improvements in Noni. I like the drop down menus and the fact she tries to help you navigate the site. She still struggles to give the right responses. She asked how I was and I said ok and she told me she was sorry to hear that.
@brilliantTurtle89 doh! thanks for being patient with her :)
@GlenM
Just tried out the new Noni. I remember the first time I interacted with her when I joined in 2020 it was quite a mess. Eventually the conversation kind of came to a dead-end and I ended up leaving her up the recesses of my chatbox for awhile lol. I got to say, interacting with her now has much greatly improved since before! I mentioned this somewhere in my Forms response, but while I still think there is a lot to go before this program could successfully emulate a real-time listener, it definitely starting to know what to say to certain responses. Strictly removing the idea that Noni is a program to begin with, her responses definitely align more with compassion, formulating the "right" things to say in response to certain situations. It also properly walks the tightrope of supporting without giving advice too! Some little qualms I saw with interacting with the program.
1. a bit generic responses. While I appreciate the load of specific messages Noni gives, it could use a bit more specification as a natural conversation does. (which I know is much much easier than done.)
2. While I love the idea of utilizing AI to support our duties as listeners, I find it still difficult to believe if many people would be willing to use such. I feel as if just the idea of talking to a "bot" or a "program" can undermine compassionate care. Perhaps, Noni is the forefront of overturning that conception!
3. some small bugs that previous listeners and testers have mentioned. My own funny experience is that Noni thought my name was "My name is Sunny" and called me that for the whole conversation I had with her. Cute!
@sunnyWriting4806 thank you for this comprehensive feedback! I appreciate it. Yes, 100% Noni is not a replacement, but a support for listeners and members. Human to human connection is what 7 Cups is all about and we need tech to support that objective through and through.
We are going to keep working on her and she'll get smarter over time. For example, she'll be able to answer questions and be less repetitive. We'll get there one step at a time!
@GlenM
Noni is greatly improved, amazing work team! ❤ I have always loved chatting with her when nobody is around. But the improvements have made her fantastic!
The only thing where I felt Noni could be improved is not repeating the same responses to different questions. I had a good chat with her and she was quite repetitive multiple times, even when I changed the question. I felt, this part could be improved a bit because the same responses repeatedly to different questions, makes it a bit irritating.
Apart from that, she is doing amazing! She is compassionate, professional and sweet. In future, maybe information about roles, community managers, etc could be added as well but at a present state, she is doing great!
A huge thanks to the team for working hard to help improve Noni and her responses. She is phenomenal! ❤
@SuryanshSingh thank you for the feedback! Believe it or not, repetition is something we did a lot of work on, but we have more work to do! We will make some updates to her this week that should help with this. Thanks for helping us out!
@GlenM
Noni is so so much better now, Glen! I really appreciate the hard work the amazing team behind Noni did. She is amazing, overall! Thank you all ❤ Wishing the best!
@GlenM I used NOni a little bit. I think that for someone that wants to vent and have someone listen Noni seems very reassuring.
I admire the time and effort put into improving Noni and they seem more compassionate. I worry that if we do not vary their responses more that people may feel like they keep saying similar things. I think maybe with some more open-ended questions thrown in that people may be encouraged to open up.
As a long time listener, one thing I noticed was a lack of Noni asking open ended questions. They seem to repeat the theme "Let's return our focus to how you're feeling today" or something similar. Once or twice is fine but some members need an invitation to open up.
Here are some open ended questions that begin with How or What
How has your experience of life been lately?
What kind of challenges do you face?
What kinds of things help you cope every day?
What kinds of activities take you out of worrying about your challenges?
If you were listening to a friend with similar challenges, what might you say to them to reassure them?
Do you want a link to any of the free resources at 7 Cups?
Would you prefer group activities [if so link to group support rooms or sharing circle], one on one [If so link to browse for a listener or therapy community] or working by yourself (Self Help Guides, Growth Paths)?
How would you describe how you spend most of your days?
What kind of pets do you have?
What is the most fun thing you can remember?
These are just a few that might be sprinkled in so it sounds like Noni is not robotic even if they are a bot.
@GlenM
I disagree with the whole noni and ai because it doesnt and cant do everything a human can and noni and ai give a false sense that someone is listening. that is why i turned off noni and other reasons i turned off noni. There is more to technology and people arent using it well at all
Hey @blissfulTouch29
Hope you're doing well!
I see where you're coming from here but I wanted to ask you a few questions to better understand your point of view.
First of all, what would you consider good or appropriate use of tech like AI?
Secondly, why do you think this is a bad or negative use of AI?
I just wanna be clear here, I do not in any way mean to undermine or discredit your point. I just want to better understand it and see if there is some mutually acceptable resolution that we can reach in this issue.
Have a nice day!
@Mahad2804
1. Maybe a good or appropriate use of AI or technology would be to help buildings make things in large amounts but also have workers work and also for prosthetics.
2. the negative is that AI cant do or experience human emotions and that people are abusing AI and technology whether it is in schools or in real life people are losing manners and are more focused on technology than reality it is a proven fact that technology/ AI does more harm than good.
@blissfulTouch29
Here's why I think Noni fits those rules of dos and don'ts that you outlined:
You say that AI should be used for routine, repetitive tasks. I'm assuming that's because we want to spare the human populace to work on more thought-intensive fields like inventions, theoretical sciences, and philosophy.
I think the primary function of Noni, and what most people will be using it for, are those menial, repetitive tasks like asking for instructions or giving reminders.
Say you want to know how to make a new forum post but don't wanna dig through forums to find an answer and the chatrooms happen to be empty at the moment. This is precisely the kind of thing Noni can help you with (well it isn't able to do that atm but that's just an example).
What Noni isn't made for is replacing listeners. It can't do the job, it isn't doing it, and it never will do it. I agree with you that students have been misusing AI to cheat on school work but that is a very short-term, low-risk consequence when we look at the overall benefit we get from tech like this.
I'll give you a real-life example here. I am a CS student and I like to do programming as a hobby. There's a very popular tool among the programmer community nowadays called Github Copilot. It is an AI-powered code autocomplete system. How it works is when you're typing down code, it passes suggestions as to what you might want the next word, or line, or few lines to be.
Now at first glance, you might say I'm cheating because I'm only doing half the work if AI is writing the other half of my lines for me. But if you've used it you'll see that most of what it does is take care of boilerplate.
For example, if I have been writing some HTML for a webpage and I have been using the same pattern over and over again. Say, I'm creating a large form for a survey. Now in this form, there are multiple input fields. Each input field is surrounded by a parent element called a "div" for some style and layout purposes. If I code 2 or 3 input fields like this, on the next one, the AI will automatically suggest the core structure of the element to me because it knows that's what I've been doing for the past X lines.
Now does this mean I can get my work done quicker?
Yes, it definitely does.
Does it mean I am dishonest in saying "I did the work"?
No, I don't think so because even if I didn't write the code the next 5-10 times, it was my initial code that the AI used to recommend the next parts.
And even though this is only one example, I think this will hold true across most, if not all fields. Excluding education, and even in that field only malicious use by students; I think AI does the professional world a lot more good than harm.
It makes us more efficient, less prone to human error, and helps out tons in repetitive, logical tasks.
Getting back to cups and Noni, I think the use of AI is highly beneficial here and it will bring so much good to the community. We've all tested it first hand and know that there are significant guardrails in place to keep this AI from returning harmful responses and I think given enough time and attention, this will grow to become even more smarter, interactive and helpful for all the users of this site.
Now I understand you have a different point of view on this issue and I would very much like to hear it. You may have concerns I haven't thought of and it's possible I might be wrong about this issue as well. So go ahead and drop your views below and I would love to discuss this further.
(P.S You mentioned in your bio that you love NCIS and I have to say, your in TV is impeccable. That is such a great show and I'm absolutely obsessed with it as well. Although I didn't like that they cut out Gibbs, it's losing that touch without him there. I would love to hear your thoughts about this as well, though maybe not here. If you're interested in discussing TV and Movies, I suggest you check out the TV and Movies community)
I was thinking of all of this great feedback last night and had an idea of a sort of Noni hacks crew. I look at Noni as a thinking tool or a sort of interactive journal. There are things we can do as users that increase her helpfulness. Here are some hacks I've learned:
1. If I provide a longer response with more context she tends to do a better job.
2. If I just choose one part of her message that resonates most with me and just respond to that part and ignore the rest.
3. If she is getting repetitive, I just stay focused on what I want to talk about and she eventually catches on.
This makes me wonder if there are other easy ways / hacks we can do to help her do better. If anyone is game for helping me uncover and/or list these hacks out, then that would greatly be appreciated.
You can see these ideas as helping her do a better job from one side of the continuum. On the other side, we'll be releasing updates to her to also help her improve. So perhaps changes from both sides will meet in the middle and help her improve overall.
Quite good !!! Loves it 💯💯💯💯💯💕💕💕💕💕💕