This is decent for what it is. Some of the problems are pretty open ended which has pros and cons, but that is very different from leetcode, which has very specific data and test cases.
For example, implement linear regression but the example solution uses a random number generator without a fixed seed. It’s fine, reproducibility isn’t the point, but leetcode problems are more structured.
In leetcode they usually don’t tell you exactly what data structure you must use, only that it must pass certain test cases. By analogy this might not tell you which architecture to use but require that it passes certain eval metrics.
Exorust 17 days ago [-]
I hoped that it would be a little open ended as most questions in ML in real life are open ended.
janalsncm 16 days ago [-]
Most ML problems in real life don’t constrain you to use linear regression or a CNN either. But there will be some metric you need to optimize.
What would take this repo to the next level is to have a reproducible data generation function for each exercise as well as a reasonable metric which must be passed. I don’t see anything that requires my classification auc to be over 0.5 which would be a basic criteria of bug-free code.
Exorust 16 days ago [-]
It's also what most people ask when they go for interviews.
I was reverse engineering the ML interview pipeline for myself and that's how I stumbled upon all this.
I think the data aspect does make sense tho. I might add that as the next thing to do
gerroo 17 days ago [-]
Cool idea, will try. Since it seems mostly llm generated you could publish the process and prompts for transparency.
Exorust 17 days ago [-]
I'll do that.
I'll also add a disclosure that I did use Gpt to generate it.
only-one1701 17 days ago [-]
> Avoid using GPT. Try to solve these problems on your own. The goal is to learn and understand PyTorch concepts deeply.
I mean...this entire project appears to be mostly GPT-generated?
mumbisChungo 17 days ago [-]
One time my teacher used a computer to make a math test for me, but then told me I couldn't use my computer during the exam. I dropped out of school immediately.
only-one1701 17 days ago [-]
Great analogy my brother there’s minimal difference between a word processing software and an LLM
notathinker 15 days ago [-]
The purpose of the project is learning. The author believes that avoiding GPT will help you learn more effectively and offers that as upfront guidance. In this case, “avoid using GPT” isn’t an ethical directive but simply a learning recommendation. The value of that advice isn’t tied to which tools were used to create the question set.
only-one1701 14 days ago [-]
Did GPT write this?
YeBanKo 17 days ago [-]
Why do you think it I GPT generated?
pj_mukh 17 days ago [-]
What are people's other "go try to build this thing, perfectly aligned to your noob-level" ways of learning lower-level ML Tools (PyTorch, CUDA etc.)?
cwlcwlcwlingg 16 days ago [-]
It helps me a lot!!
oezi 17 days ago [-]
Is it just me or does anyone else find the red squiggly lines under Pytorch and Leet hilarious in the heading picture?
Exorust 17 days ago [-]
Ah god damn it.
arnab_optimatik 17 days ago [-]
super helpful, thanks for sharing!
17 days ago [-]
17 days ago [-]
lihaciudaniel 17 days ago [-]
[dead]
saltserv 17 days ago [-]
[dead]
thehamkercat 17 days ago [-]
[flagged]
cinntaile 17 days ago [-]
Why does he have to delete it?
throwawayoldie 17 days ago [-]
OP _did_ say "please".
NetRunnerSu 17 days ago [-]
[flagged]
raincole 17 days ago [-]
^ This is a bot/crackpot account whose only purpose is promoting jumbled words on HN. How/where to report it?
Reminds me of some of Xah Lee's earliest posts on the Python mailing lists. Many, myself included, thought he was a clever bot.
anonymoushn 17 days ago [-]
Accounts with high karma have a "flag" link in the header of comments and submissions for indicating that it may not be the right kind of content for the site. Human moderators actively monitor the site, so your comment about this user's behavior will be seen by one of them soon.
satvikpendem 17 days ago [-]
Email hn@ycombinator.com
Rendered at 02:41:55 GMT+0000 (UTC) with Wasmer Edge.
For example, implement linear regression but the example solution uses a random number generator without a fixed seed. It’s fine, reproducibility isn’t the point, but leetcode problems are more structured.
In leetcode they usually don’t tell you exactly what data structure you must use, only that it must pass certain test cases. By analogy this might not tell you which architecture to use but require that it passes certain eval metrics.
What would take this repo to the next level is to have a reproducible data generation function for each exercise as well as a reasonable metric which must be passed. I don’t see anything that requires my classification auc to be over 0.5 which would be a basic criteria of bug-free code.
I was reverse engineering the ML interview pipeline for myself and that's how I stumbled upon all this.
I think the data aspect does make sense tho. I might add that as the next thing to do
I mean...this entire project appears to be mostly GPT-generated?
[0]: https://news.ycombinator.com/submitted?id=NetRunnerSu