Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Time travel debugging AI for more reliable vibe coding

nut.new

Post reply on HN
Print view View original

41–50 of 57 posts

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#41

Post by SparkyMcUnicorn »

ScrexyScroo wrote: post #35

LLMs at best are a good auto-complete. I have been trying to use LLMs to code since GPT 3 came out. While Claude 3.7 has made some progress still it can't generate an app into existence, although it's great for boilerplate or hinting to which direction I should try to find the documentation.

In the past week I created two apps within 3-5 iterations. No manual edits (other than .env).

Another one I thought was pretty cool was handing it some API docs for something, then had it build a UI and admin interface from scratch.

The dev agent tools these days aren't half bad, and they're getting better.

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#42

Post by anonzzzies »

vunderba wrote: post #39
unclad5968 wrote: post #14

What is vibe coding?

An even lazier form of LLM assisted coding where you blindly spam the tab key without even taking the bare minimum amount of time reviewing the garbage that it's busy outputting. Karpathy "coined" the term and I absolutely hate it. It's up there with "asshat" and "awesome sauce" for profoundly stupid terms.

I find it more akin to prompt engineering; something else that is nothing more than 'typing some shit until it does something useful to someone' and then acting like it's actually a skill.

But we are very good in our profession to make up garbage terms to do anything but describe garbage.

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#43

Post by anonzzzies »

ScrexyScroo wrote: post #35

LLMs at best are a good auto-complete. I have been trying to use LLMs to code since GPT 3 came out. While Claude 3.7 has made some progress still it can't generate an app into existence, although it's great for boilerplate or hinting to which direction I should try to find the documentation.

That hasn't been true since 3.5; it can and does generate full working code and sometimes with only a few attempts. Sometimes it cannot figure it out and then you need to fix it yourself as it will just loop forever. These things can be absolutely trivial (and thus frustrating) at times, but it's also fairly magical when it just does work.

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#44

Post by curioussavage »

bhackett wrote: post #20
ryandrake wrote: post #16

Earlier quoted context omitted.

The way I understood it: Cobbling a program together by simply prompting AI assistants over and over, blindly using the generated code, and repeating until it barely approaches satisfying the requirements. Not worrying about things like correctness, proper design, code cleanliness, understandability, performance, code size, security, data protection, maintainability, or even bugs unless they catastrophically stop the…

Yes, that's all true. Even so, vibe coding empowers anyone who can write clear instructions to build software, but the limits of the technology get hit pretty quickly by non-developers and they have little recourse. This blog post https://addyo.substack.com/p/the-70-problem-hard-truths-abou... is a great overview. The tech will get better and better (I couldn't imagine we'd be doing this a year ago) but to be truly u…

I’m sure it will. My pessimistic take is that the worst case is that thousands of bozos create crappy little apps that only cause minimal harm. And people just endure it instead of pushing for better guard rails.

Best case is some high profile shit show caused by software made mostly or entirely by ai that hopefully is bad enough that legislators wake up and realize that in the modern world software is essential enough that you can’t let just anyone sell it or services based on it. Just like you can’t allow anybody design/build bridges or hardware or whatever.

But I’m sure thats wishful thinking. Hacks and buggy software causing consumers harm is just accepted and software industry folk all hope to be billionaires so nobody cares.

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#45

Post by liamkearney »

AdieuToLogic wrote: post #34

> AIs are really good at writing code but really bad at debugging -- it's amazing to use Claude to prompt an app into existence, and pretty frustrating when that app doesn't work right and Claude is all thumbs fixing the problem. LLM's are not "really good at writing code". They generate statistically relevant text based on their training data set. Expecting people who do not understand code to use LLM’s for making s…

Exactly my annoying exert as well. LLMs are good at debugging not writing code.

It’s just a statistical rubber duck, “what other obvious (common) things haven’t I thought about yet Mr duck?”

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#46

Post by colordrops »

webdever wrote: post #26

> it's amazing to use Claude to prompt an app into existence, and pretty frustrating when that app doesn't work right and Claude is all thumbs fixing the problem. Such an in interesting sentence. App that doesn't work doesn't seem like it's yet come into existence. This has been my (limited) experience so far. I haven't been able to get an AI/LLM to help me build an app. Even React apps it fails at. I have been able…

The first pass often executes but the "thumbs" come in when you fix corner cases or iterate on it.

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#47

Post by becquerel »

AdieuToLogic wrote: post #34

> AIs are really good at writing code but really bad at debugging -- it's amazing to use Claude to prompt an app into existence, and pretty frustrating when that app doesn't work right and Claude is all thumbs fixing the problem. LLM's are not "really good at writing code". They generate statistically relevant text based on their training data set. Expecting people who do not understand code to use LLM’s for making s…

This is the worst kind of pedantry. There is now code in a text file that wasn't there before. It doesn't really matter to me if they code came from human fingers, an auto generator tool, an LLM or a ouija board. It looks like written code and it compiles like written code - it's written code. You can rightly criticise the use of LLMs in many ways but it is more useful to focus on the actual reasons they cause harm than to set red lines over language.

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#48

Post by strbean »

ScrexyScroo wrote: post #35

LLMs at best are a good auto-complete. I have been trying to use LLMs to code since GPT 3 came out. While Claude 3.7 has made some progress still it can't generate an app into existence, although it's great for boilerplate or hinting to which direction I should try to find the documentation.

Have you tried this tool?

I just generated two tetris games, one with ascii art and one with WebGL, and I found it quite impressive. Maybe simplistic apps, but still quite impressive with it's ability to create functional games and fix bugs with minor prodding.

Re: Show HN: Time travel debugging AI for more reliable vibe coding

#50

Post by leptons »

becquerel wrote: post #47
AdieuToLogic wrote: post #34

> AIs are really good at writing code but really bad at debugging -- it's amazing to use Claude to prompt an app into existence, and pretty frustrating when that app doesn't work right and Claude is all thumbs fixing the problem. LLM's are not "really good at writing code". They generate statistically relevant text based on their training data set. Expecting people who do not understand code to use LLM’s for making s…

This is the worst kind of pedantry. There is now code in a text file that wasn't there before. It doesn't really matter to me if they code came from human fingers, an auto generator tool, an LLM or a ouija board. It looks like written code and it compiles like written code - it's written code. You can rightly criticise the use of LLMs in many ways but it is more useful to focus on the actual reasons they cause harm t…

> It looks like written code and it compiles like written code - it's written code.

And more often than not it's just plain wrong code. LLMs aren't actually writing code, they are guessing at what might satisfy an input. Writing code is more than guessing, it's about assembling instructions with intent, for a purpose. LLMs lack that intent and purpose.

> You can rightly criticise the use of LLMs in many ways but it is more useful to focus on the actual reasons they cause harm than to set red lines over language.

The "actual reasons" they cause harm are inherent to how LLMs work. The real problem is people not understanding how they work and placing too much trust and in them and believing the hype. They are not some miracle, they aren't even all that helpful, and in my experience they are more of a waste of my time.

Post reply on HN