I'm bad at LeetCode. I keep memorizing solutions to problems instead of actually learning the concepts. That's why I built ClankerRank ( - AI-generated problems to help you confidently prepare for any coding interview. Free + open source!

Throw me a star if you can :) Built using @bunjavascript, @nextjs, @aisdk, @honojs, and @Cloudflare sandboxes + workflows

@nextjs @aisdk @honojs @Cloudflare Damn, in 24 hours! This was just a side project I built for myself over Thanksgiving and thought I’d share. Yes, it’s buggy, fixing 🫡🛠️

diabolical name

if they ever find out I’m cooked

@will__ye We found out. Great concept though, will try it out.

@will__ye lmao i meant if the clankers ever find out 😭

Interesting name. Agree with you on building a platform for learning the concepts instead of memorizing solutions. Happy to connect sometime to understand more. Drop a note to hari @ hackerrank if you are interested.

Honored to have made it to your feed! Emailed you :)

This works till you see LLM generate some bullshit test cases and logically ill sounded bullshit questions. It can easily fuckup even if you ask a leetcode question and ask it to diverge from editorial solution, and it goes absolutely bonkers

absolutely! far from perfect, but there’s a few guardrails you can put in place. for example, LLMs can def hallucinate entire test cases, but you can use LLMs to describe test cases (“a large nondecreasing array of prime numbers”), then use that description to generate code to generate test case inputs. run the solution through those inputs to get expected outputs. the tricky part is in a hallucinated solution, but there’s likely ways to use LLM as a judge here. this is just standard leetcode, not IOI, so shouldn’t be too crazy

Guard rails take you to a particular level, but let us say for a 2D array of arrays, it just gives bullshit output for a given input, and you ask it to check again it gives a different answer, Only way to solve this is generate test cases using the correct code, which is not confirmed to be correct if written by a LLM. But could definitely be an accelerator for this purpose

yeah so the LLM generates code to generate appropriate inputs and then a solution. it runs the inputs through the solution to get the expected output, preventing the case in which you get different expected outputs every time. the only real problems are in bad input generation code (not likely, pretty trivial to do write code to generate a string/array/number that fits a certain constraint) or a bad solution. bad solution is decently mitigated with LLM as a judge. all in all practical worst case is you can just regenerate a problem haha

Yep, only case this remotely works or illuses to work, is when we run the solution for generated test cases in our execution environment, rather LLM assuming the output

I am also bad at Leetcode , we should chat! haha

This is cool! Would love to check this out, maybe a quick idea would be to have a section which lets this AI help you understand Advent of Code?

Ooo super interesting! Can look, but also wouldn't mind if you opened a PR!

Yeah something like a plug-in where in you can choose from previous year questions and on going questions. Will take a look asw, gave it a star!

@MehtaDontStop 👏

that’s cool! 👌🏼

thanks! first time using cloudflare, you guys are killing it!

let me know if there is anything we can improve on sandboxes and make things better

This is exactly what intern needs today.

would love for you to try!

Great! But I had one question In leetcode we see many times all LLMs can’t solve hard problems and sometimes medium. So how do we know that the AI generated problem and test cases are correct?

You're right, this isn't perfect! For now, a sanity check I have is the custom test cases you see in the lower half of the right side. If those don't look right, it's probably a smell. In that case, you can always regenerate a problem!

Yeah, maybe something like llm council can solve this problem?

Hi Kamath from another Kamath Super Project kella Tuva Anna

good job. will use this

Thanks! DM me if you run into issues!

Much needed 🫠

Lmk how it goes for you!

tried it full of bugs

PRs welcome!

Goat

cool

Tried it but this UI must have been vibe coded.

Ah it’s not really meant for mobile use yet :/

Nice one

Love this idea! Finally, a tool to focus on concepts, not just solutions 💡

Well thats cool

awesome

whats the point making a new one with easier difficulties while the point of grinding it is to practice harder questions?

Great work👍

Oh

Can I contribute to it ????

Impressive Share

which app was used to record and edit the demo video?

Great project 👌, One more thing how can I create a demo video like this for my project?

@screenstudio

Coding interview

I'm jealous you got this banger domain

just had a look dope for leetcode practice love the fact AI generates consistent problems let's launch/spotlight you mate on if that helps or just for fun ;)

Good on you, Anirudh, memorizing is a shortcut but understanding is the real deal, no?

Amazing share

Why this world is cruel to me , Whenever I get an idea , it then gets snatched by someone , see !!!🥲😭😭