Live data from Hacker News

Show HN: Workout.cool – Open-source fitness coaching platform

github.com

81–90 of 248 posts

Re: Show HN: Workout.cool – Open-source fitness coaching platform

#83
post #49
post #46

Earlier quoted context omitted.

You know counting calories by taking a picture literally doesn't work right? In fact, I'd argue it's one of the best examples of when an LLM confidently feeds you misinformation. An obvious example, a chicken breast fried in oil and a chicken breast air fried look identical, yet the oil fried one would have 3-4x the calories at least. Don't take my work for it though - this was just on HN the other day: https://news.…

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 the picture upload or context?

Re: Show HN: Workout.cool – Open-source fitness coaching platform

#84
post #46

Earlier quoted context omitted.

You know counting calories by taking a picture literally doesn't work right? In fact, I'd argue it's one of the best examples of when an LLM confidently feeds you misinformation. An obvious example, a chicken breast fried in oil and a chicken breast air fried look identical, yet the oil fried one would have 3-4x the calories at least. Don't take my work for it though - this was just on HN the other day: https://news.…

I agree in principle, but I'll say that the number of calories are likely not 3-4x. The 3-4x number is for deep frying chicken. You usually don't do that if you aren't also breading the chicken. A pan-fried chicken with a little oil in the pan to avoid sticking/make better thermal contact will add calories but not 3-4x more. You're likely using about 1 tbsp of oil which is around 100 kcal. 100g of chicken has around…

Not if you eat out at well known healthy chains they already have their nutrition details on their sites that AI pulls from.

Re: Show HN: Workout.cool – Open-source fitness coaching platform

#85
post #38

Earlier quoted context omitted.

I got the same error.

Yes totally unexpected! It is fixed right now. Traffic spiked and my backend rate limits kicked in too hard. Thanks so much for trying it out

I'm still getting the same error

Re: Show HN: Workout.cool – Open-source fitness coaching platform

#86
Got an error when trying to build a workout. Looks useful though! When I travel I only have bands if there are no local gyms offering reasonable prices, and doing the same 3 workouts gets boring

https://imgur.com/a/Z71iT65

One thing that would be super nice, make the back button and forward button work. Its really tempting to want to hit the back button when you select equipment, click next, and realized you missed one.

Re: Show HN: Workout.cool – Open-source fitness coaching platform

#88

Am not sure what your data source is, but l run the following: - https://wrkout.xyz/ (exercise database api with images and videos) - https://github.com/wrkout/exercises.json (open source exercise dataset) If they are of any interest / help

Hey actually came across wrkout.xyz a while back, really cool project!

For this, i rebuilt the entire dataset from scratch with a partner to avoid any licensing ambiguity (especially with videos), and to have full control over attributes, translations, etc.

But I absolutely love seeing other open projects in this space and I'd be happy to explore possible synergies if it can help both communities.

DMs open !

Re: Show HN: Workout.cool – Open-source fitness coaching platform

#90

It would be great if the equipment and muscle selection wasn't mandatory. For example, I have a pull-up bar but I have no idea what muscles I can train with it. Why not let me filter on beginner exercises instead?

Mh yeah i didn't expect that but it shows that the current flow assumes a bit too much knowledge up front, I"ve heard similar feedback from others.

I'm already planning to make the filters optional, and add things like "beginner-friendly", "popular exercises", "calisthetics", ...

Thanks for pointing it out

Post reply on HN