AI climbing coach
AI
computer vision biomechanics
SHOW HN2024
320points
141comments
#180of 3,515 in 2024
Top 6%of 2024 by points
How HN took it
DebatedReal support and real criticism
19 positive, 26 neutral or asking, 7 mixed, 20 critical, out of 72 comments about the project. Thread score +0.03.
Idea: 12 for, 15 againstExecution: 1 for, 4 againstPrivacy: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive technical execution and cool idea
From 3 comments
Not a climber myself but this is super impressive. Curious about what techniques you’re using. Is this based on a GAN model?
programmarchy on HNI look forward to playing with this. It seems astonishing.
jfengel on HNVery nice. Please do open it up as much as possible. I'm curious about the data pipeline. I love bouldering and have thought about different ML ideas in that domain. I'm also an…
kriro on HN
Could be useful for novices
From 2 comments
Looks cool! It definitely looks technically challenging, especially for expert climbers who have a variety of creative moves at their disposal. But I can definitely see this…
teapourer on HNCool idea! My friends and I have chatted about building something similar, though with a coaching focus. Specifically for use with spray walls/kilterboards/etc. It could be…
alexcaza on HN
Objections
Removes the problem-solving fun of climbing
From 4 comments
One of the most fun part of climbing is the problem-solving aspect of it. Figuring your way to get up the wall/boulder. Why would you want to get rid of that?
kettunen on HNThis is really cool from a technology point of view but the main attraction of climbing for me is figuring out how to "solve" the climb. Trying to solve a crux with a buddy is…
hangonhn on HNIf anyone would actually use this (I don't think they would, because the puzzle, and talking about beta is half the fun of climbing)... ...then this would be very valuable data.…
i_am_a_squirrel on HNI feel like I’m the right audience for this - a not very good climber with unusual distribution of limbs. But I’m not interested - part of the fun in climbing is on sight climbs…
Temporary_31337 on HN
Hold recognition and 3D wall geometry likely inaccurate
From 3 comments
It looks really interesting, but as an experienced climber I'm not sure if just watching a video of my avatar climbing would really help with skill acquisition. Also, this claims…
prions on HNI'm sceptical about the usefulness of this for a number of reasons, including the points raised by others about hold recognition etc. It's also difficult to see how the system…
lambdaone on HNI'm genuinely curious how the model classifies holds. I could (hypothetically) see this doing something like assigning more utility to certain holds (e.g. a steep sloper that is…
ropable on HN
Ignores strength and flexibility differences
From 2 comments
Very cool idea but I wonder how well this can possibly work in practice. So many bouldering problems hinge on small things, such as how a little crimp hold is oriented or how…
copypasterepeat on HNThis has always been a dream, because there is a "perfect" way for your body to climb a route but it would be insanely complex to calculate, especially when factoring in every…
ericmcer on HN
Requests
Open source the model and code
From 2 comments
Very nice. Please do open it up as much as possible. I'm curious about the data pipeline. I love bouldering and have thought about different ML ideas in that domain. I'm also an…
kriro on HNVery interesting, do wish we could play with it since it is a show hn, maybe repost when it is open sourced/usable. Looking forward to reading about how it works. How does it…
aconz2 on HN
Let people try the hosted demo
From 2 comments
Very interesting, do wish we could play with it since it is a show hn, maybe repost when it is open sourced/usable. Looking forward to reading about how it works. How does it…
aconz2 on HNI look forward to playing with this. It seems astonishing.
jfengel on HN
Questions
How does it classify holds and infer 3D geometry
From 3 comments
I'm genuinely curious how the model classifies holds. I could (hypothetically) see this doing something like assigning more utility to certain holds (e.g. a steep sloper that is…
ropable on HNA few thoughts as I've done academic research & built products in this area: - if you're using SMPL body parameters this will have to stay research / open-source - is this…
goodmattg on HNVery interesting, do wish we could play with it since it is a show hn, maybe repost when it is open sourced/usable. Looking forward to reading about how it works. How does it…
aconz2 on HN
Is it based on a GAN or what architecture
From 2 comments
Not a climber myself but this is super impressive. Curious about what techniques you’re using. Is this based on a GAN model?
programmarchy on HNVery cool!! I am unfortunately very far from an AI expert. Can you share how you built this? Did you have to train your own model, or is it an open source model that you…
silentsea90 on HN