141–150 of 248 posts
I guess Sign in with Apple costs money compared to Sign in with Google, right?
But you do need to have an active Apple Developer account (which is $99/year) to set it up and maintain it.
Earlier quoted context omitted.
What happens if you give it that context though? Or prompt it to search the web for comparable meals?
At that point I just have to ask what the AI is actually doing for you? I can just hit a search engine and say "number of calories in X" and get a precise answer with 2 seconds of calculator math. If I have to take a picture, send it to ai, but then amend it with "This is air fried chicken, it weighs x, it's a breast cut. I didn't add salt." Why do all that when a single search will give me the answer I want without…
Curious on the design decision to have a server backend, instead of just offloading everything to the client to avoid the hug of death issue and server costs.
I choose to keep a server backend for a few key reasons:
- Centralized updates to the exercise database (videos, translations, attributes) without shipping a new frontend each time. (The goal is to have 5 to 10 new exercices per week)
- The ability to offer shared features like community workouts, saved routines, and (eventually) syncing across devices, etC...
Room to grow into more advanced features like progression tracking, public/privates APIs (strava, garmin, ...), and integrations all of which are much harder to manage purely client-side in my humble opinion.
I was just poking around, but how/why aren't there issues with the videos now. Sure you're just embedding youtube videos, but what's to stop them from taking that down? Are there really no open licensed workout-movement animations out there? That sounds like a fun beginner animation project honestly.
I wanted to make sure everything is legally safe and not just scraped or reused without rights.
Producing proper 3D exercise videos is actually VERY expensive we’re talking €10–20 per animation, or thousands of euros per month if you go through a good/high quality API provider. That’s why it's such a tough space for open-source tools to compete in.
Long-term, I'd love to help build a community-driven, open-licensed library of movement animations but until then, this partnership was the best balance between cost, legality, and quality.
Thanks for raising it
This is awesome! Thanks for sharing :-)
Earlier quoted context omitted.
From what I can see this is AI generated, and it doesn't work when you press continue.
I think the servers can’t handle the high traffic from HN, you can clone the repo and run your own
It appears to be hosted on Vercel...
Earlier quoted context omitted.
You generally want to make sure you're working out specific muscles or muscle groups a certain of times each week and with a certain number of working sets, rather than "I have used $MACHINE recently so I need to do that today."
I only have dumbbells, so selecting the equipment first is actually ideal for me
Wow, this doesn't suck at all. The thing that's missing for me is suggestions on how much to lift / how many reps. There's a fitness program called 100 Pushups that came up with a good solution for that… - Repeat the exercise (in this case, a push-up) as many times as possible until failure. A person might achieve 8, for example. - The app comes up with a schedule; every other day, the user is expected to do a set of…
I love that idea. Yeah i know this app : it is a great example of how simple, adaptive progression can really motivate people (specially beginners). And yes I'd absolutely be interested in discussing a UI + flow for a self-adjusting progression system like that. Yeah. Let's talk about that, drop me a DM? I can think about some (ugly) alhorithm first
It might be better to focus not on generating routines from scratch for users, but rather logging existing workouts, and importing routines/templates other people have designed. (I know you expressed interested in working on the latter in the comments here.)
Some specific issues I encountered:
1. I said that I wanted a full-ish body workout, and it recommended 33 distinct exercises for a single session. That's wildly impractical.
2. The exercise selection seems to just pick 3 random lifts (based on available equipment) for each selected muscle group and ignores the fact that many lifts hit more than one muscle group at a time. It also disregards the widely accepted notion that certain muscle groups respond better to different training volumes.
3. The selection of specific exercises seems arbitrary, recommending some that are very far out of the mainstream and with poor resistance curves.
4. It recommended exercises with equipment I do not have (I'm a home gym person - no way to exclude machines)
5. It suggests strange branded equipment (e.g., "Dynaband Shoulder Press")
6. If you go back to select different equipment, it will continue to recommend exercises with that equipment.
7. Can't delete recommended exercises, nor even add new ones.