@julia_shinkevich1 haha thank you Julia! We work a lot to make our therapist feels much closer to real human than just to ChatGPT! We glad you see that :)
@julia_shinkevich1 Thank you! Really appreciate that - we know many people have been using ChatGPT for emotional support, and we're glad Lovon feels like a step up.
What was missing for you in ChatGPT that you'd hope to find in a dedicated therapy app?
Report
Love the voice-first approach! Typing feelings is exhausting - you start to overthink. Voice unlocks something more natural.
Also respect the focus on "challenging unhealthy thinking" instead of just agreeing. That's what real therapy does. Congrats on the launch and $850K! 🎉
@virtualviki Thank you! You nailed exactly why we went voice-first - there's something about speaking that bypasses overthinking and gets straight to how you actually feel. Text can feel like writing an essay about your emotions 😅
What kind of stuff do you usually find yourself overthinking about?
Report
@ponikarovskii constantly re-read my messages checking for grammar mistakes and then overthink if I said something wrong 😅
But the bigger thing is just the pressure to always improve. Earn more, look better, be healthier, build something meaningful. Hard to just live life when you're constantly comparing yourself to the successful 1% you see online. Social media makes it feel like everyone's crushing it while you're still figuring things out.
wow, such a great tool.. congrats on the launch! i love the idea of immediate crisis recognition and actual help with connecting to the real therapy. which languages does it support for now?
@yellow_yetti thanks a lot Vera!! Right now it is english-only, but more is to come!
Report
Maker
@yellow_yetti We have crisis management btw. If Anna will notice destructive behavior or dangerous, she will help user to connect to real therapist or emergency1
@yellow_yetti what languages would you suggest to add next?
Report
Really interesting positioning especially the clinical foundation.
From a safety perspective, how do you ensure consistency in responses over time? Is Anna aligned through fine-tuning, or do you rely on structured prompting and guardrails on top of a foundation model?
In mental health use cases, stability and drift control seem crucial, curious how you approach that.
@rachid_jeffali Thanks Rachid! Great question - it's actually both. We use fine-tuning AND structured guardrails on top of a foundation model. For us, the most critical thing is detecting potential mental health issues early and communicating them to users in time. Stability in a mental health context isn't optional, it's the whole point. What kind of drift patterns concern you most in clinical AI use cases?
Replies
Good luck with the launch! Love your app idea, I used to use ChatGpt for that, but your app is definitely better
@julia_shinkevich1 haha thank you Julia! We work a lot to make our therapist feels much closer to real human than just to ChatGPT! We glad you see that :)
@julia_shinkevich1 Thank you! Really appreciate that - we know many people have been using ChatGPT for emotional support, and we're glad Lovon feels like a step up.
What was missing for you in ChatGPT that you'd hope to find in a dedicated therapy app?
Love the voice-first approach! Typing feelings is exhausting - you start to overthink. Voice unlocks something more natural.
Also respect the focus on "challenging unhealthy thinking" instead of just agreeing. That's what real therapy does. Congrats on the launch and $850K! 🎉
@virtualviki Thank you! You nailed exactly why we went voice-first - there's something about speaking that bypasses overthinking and gets straight to how you actually feel. Text can feel like writing an essay about your emotions 😅
What kind of stuff do you usually find yourself overthinking about?
@ponikarovskii constantly re-read my messages checking for grammar mistakes and then overthink if I said something wrong 😅
But the bigger thing is just the pressure to always improve. Earn more, look better, be healthier, build something meaningful. Hard to just live life when you're constantly comparing yourself to the successful 1% you see online. Social media makes it feel like everyone's crushing it while you're still figuring things out.
@ponikarovskii @virtualviki unfortunately you're right, Viktoriia! But I hope we at Lovon is making things different in the better way!
Great work guys! Is good to see AI applied in such ways to help people. Best of luck with the launch!
@th_calafatidis Thanks Theodore! Really appreciate the support 🙏 AI in mental health is such an exciting space right now.
Have you tried any AI therapy or mental health tools yourself? Curious what's been missing in your experience!
@th_calafatidis thank you Theodore!
@rbluena Thanks so much Rabii!
@rbluena thank you, Rabii!
IMO, AI will be hugely used for diagnosing and therapies. You are spot on.
@busmark_w_nika thanks Nika!
@thxgrey You are welcome :)
@busmark_w_nika thanks, we see it completely the same way
Love the goal behind this!
@mikr13 Thank you so much, Mihir!
@mikr13 thanks a lot, Mihir!
@mikr13 thanks a lot!
Known the team for a while. Good luck!
@artem_vysotsky thank you Artem! It means a lot for us!
@thxgrey lfg
@artem_vysotsky Thanks bro!
@aleksanadr_lavrinenko always here for you guys
@artem_vysotsky thanks man!
@ponikarovskii keep up the good work!
Hey man it's prince founder of evra, congrats on your launch.
would definitely give it a shot
@princeajuzie hey Prince! thanks!!
Will oversee Evra as well!
wow, such a great tool.. congrats on the launch!
i love the idea of immediate crisis recognition and actual help with connecting to the real therapy. which languages does it support for now?
@yellow_yetti thanks a lot Vera!! Right now it is english-only, but more is to come!
@yellow_yetti We have crisis management btw. If Anna will notice destructive behavior or dangerous, she will help user to connect to real therapist or emergency1
@yellow_yetti what languages would you suggest to add next?
Really interesting positioning especially the clinical foundation.
From a safety perspective, how do you ensure consistency in responses over time?
Is Anna aligned through fine-tuning, or do you rely on structured prompting and guardrails on top of a foundation model?
In mental health use cases, stability and drift control seem crucial, curious how you approach that.
@rachid_jeffali Thanks Rachid! Great question - it's actually both. We use fine-tuning AND structured guardrails on top of a foundation model. For us, the most critical thing is detecting potential mental health issues early and communicating them to users in time. Stability in a mental health context isn't optional, it's the whole point. What kind of drift patterns concern you most in clinical AI use cases?
@rachid_jeffali thanks a lot, Rachid! Appreciate!