Ask HN: What are you working on? (March 2025)

Suggestions by this platform wouldn't interfere with treatment protocol straight away; it wouldn't ask the patient to stop medicines their doctor has prescribed, or itself prescribe scheduled drugs.

It will suggest complementary interventions. Case in point: anxiety, depression, brain degeneration & other related diseases - there's Rhonda Patrick's protocol of HIIT exercises to breach the blood-brain barrier & deliver positive effects; there's Dr Chris Palmer's method of looking at metabolism & mental health jointly & benefits of a keto diet to solve such issues.

Likewise, there can suggestions from Yoga-Pranayama where deep breathing can solve insomnia & hence other diseases downstream such as hypertension in many cases.

After being on such complementary protocols, the patient's suffering will be reduced, but also the body will heal enough to an extent that their local doctor could reduce/stop medication.

The tech is in the platform, combing through wisdom of all such complementary protocols for a start. If it gains traction, we could start involving experts have system route some queries specifically to them.

I have experience building the ML-LLM part. Anyone wants to join me and build the full stack part?

Focusing on training and fine-tuning, because of lower bandwith requirements.

We're collaborating with a few AI researchers through offering a sponsorhips program for the right people. If you know anyone, send them our way.

PS. If anyone has experience with Marimo, give me shout!

[1] https://enverge.ai/

I think its impact on watch time depends on your goal of that session. When I'm in "looking for a specific answer" mode it does reduce my watch time, but there's plenty of times when I just want to watch youtube–and when I do, it helps me find what to watch, rather than reducing my watch time per se.

We don’t train on user chats directly. Instead, we collaborate with a team of 42 certified psychologists who work with us to curate anonymized case structures, decision trees, and response strategies based on real but depersonalized therapeutic experience.

These professionals help us model how psychological support is provided — without ever using actual user conversations. Our system is trained on synthesized, anonymized session data that reflects best practices, not private logs.

It’s not buried in the T&Cs — we’re very explicit about our commitment to data ethics and user safety. No session data is used for model training, and user interaction is fully confidential and never stored in a way that links it to identities.

Our goal is to make high-quality support available without compromising trust. Let me know if you’d like more technical or ethical detail — happy to share!