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

The highest quality codebase

gricha.dev

Post reply on HN
Print view View original

311–320 of 409 posts

Re: The highest quality codebase

#311

Post by skydhash »

libraryofbabel wrote: post #295
skydhash wrote: post #289

Earlier quoted context omitted.

I'm guessing, but I'm pretty sure you're dealing with big balls of mud which has dampened your love of coding. Where implementing something is more about solving accidental complexity and dealing with technical debts than actually doing the job.

I've seen some balls of mud, sure, but I don't think that's the essence of it. It's more like: 1) When I already have a rough picture of the solution to some programming task in my head up front, I do not particularly look forward to actually going and doing it. I've done enough programming that many things feel like a variation on something I've done before. Sometimes the task is its own reward because there is a su…

> 1) When I already have a rough picture of the solution to some programming task in my head up front, I do not particularly look forward to actually going and doing it.

Every time I think I have a rough picture of some solution, there's always something in the implementation that proves me wrong. Then it's reading docs and figuring whatever gotchas I've stepped into. Or where I erred in understanding the specifications. If something is that repetitive, I refactor and try to make it simple.

> I have a restless mind and I just don't find doing something that interesting anymore once I have more or less mastered it.

If I've mastered something (And I don't believe I've done so for pretty much anything), the next step is always about eliminating the tedium of interacting with that thing. Like a code generator for some framework or adding special commands to your editor for faster interaction with a project.

Re: The highest quality codebase

#312

Post by ukuina »

altmanaltman wrote: post #308
danielmarkbruce wrote: post #301

Earlier quoted context omitted.

are you really solving the problem, or is the compiler doing it?

is the compiler really solving the problem or the electricity flowing through the machine?

Is it the electricity, or is it quantum entanglement with Roko's Basilisk?

Re: The highest quality codebase

#313

Post by skydhash »

keeda wrote: post #300
altmanaltman wrote: post #291

Earlier quoted context omitted.

A few counterpoints: 1. If you don't care about code and only care about the "thing that it does when it's done", how do you solve problems in a way that is satisfying? Because you are not really solving any problem but just using the AI to do it. Is prompting more satisfying than actually solving? 2. You claim you're done "learning about coding and stretching my personal knowledge in the area" but don't you think th…

Note I'm not saying one is better than the other, but my takes: 1. The problem solving is in figuring out what to prompt, which includes correctly defining the problem, identifying a potential solution, designing an architecture, decomposing it into smaller tasks, and so on. Giving it a generic prompt like "build a fitness tracker" will result in a fully working product but it will be bland as it would be the average…

> The problem solving is in figuring out what to prompt, which includes correctly defining the problem, identifying a potential solution, designing an architecture, decomposing it into smaller tasks, and so on

Coding is just a formal specification, one that is suited to be automatically executed by a dumb machine. The nice trick is that the basic semantics units from a programming language are versatile enough to give you very powerful abstractions that can fit nicely with the solution your are designing.

> Personally, once the shape of the solution and the code is crystallized in my head typing it out is a chore

I truly believe that everyone that says that typing is a chore once they've got the shape of a solution get frustrated by the amount of bad assumptions they've made. That ranges from not having a good design in place to not learning the tools they're using and fighting it during the implementation (Like using React in an imperative manner). You may have something as extensive as a network protocol RFC, and still got hit by conflict between the specs and what works.

Re: The highest quality codebase

#314

Post by elzbardico »

snet0 wrote: post #241
bongodongobob wrote: post #215

Earlier quoted context omitted.

He means that it is heavily biased to write code, not remove, condense, refactor, etc. It wants to generate more stuff, not less.

I don't see why this would be the case.

Have you tried using a base model from HuggingFace? they can't even answer simple questions. You input a base, raw model the input

  What is the capital of the United States?
And there's a fucking big chance it will complete it as

  What is the capital of Canada?
as much as there is a chance it could complete it with an essay about the early American republican history or a sociological essay questioning the idea of Capital cities.

Impressive, but not very useful. A good base model will complete your input with things that generally make sense, usually correct, but a lot of times completely different from what you intended it to generate. They are like a very smart dog, a genius dog that was not trained and most of the time refuses to obey.

So, even simple behaviors like acting as a party in a conversation as a chat bot is something that requires fine-tuning (the result of them being the *-instruct models you find in HuggingFace). In Machine Learning parlance, what we call supervised learning.

But in the case of ChatBOT behavior, the fine-tuning is not that much complex, because we already have a good idea of what conversations look like from our training corpora, we have already encoded a lot of this during the unsupervised learning phase.

Now, let's think about editing code, not simple generating it. Let's do a simple experiment. Go to your project and issue the following command.

  claude -p --output-format stream-json "your prompt here to do some change in your code" | jq -r 'select(.type == "assistant") | .message.content[]? | select(.type? == "text") | .text'
Pay attention to the incredible amount of tool use calls that the LLMs generates on its output, now, think as this a whole conversation, does it look to you even similar to something a model would find in its training corpora?

Editing existing code, deleting it, refactoring is a way more complex operation than just generating a new function or class, it requires for the model to read the existing code, generate a plan to identify what needs to be changed and deleted, generate output with the appropriate tool calls.

Sequences of token that simply lead to create new code have basically a lower entropy, are more probable, than complex sequences that lead to editing and refactoring existing code.

Re: The highest quality codebase

#317

Post by keeda »

altmanaltman wrote: post #310
keeda wrote: post #300

Earlier quoted context omitted.

Note I'm not saying one is better than the other, but my takes: 1. The problem solving is in figuring out what to prompt, which includes correctly defining the problem, identifying a potential solution, designing an architecture, decomposing it into smaller tasks, and so on. Giving it a generic prompt like "build a fitness tracker" will result in a fully working product but it will be bland as it would be the average…

Honestly, I fundamentally disagree with this. Figuring out "what to prompt" is not problem-solving in a true sense imo. And if you're really going too deep into the problem domain, what is the point of having the code abstracted? My comment was based on you saying you don't care about the code and only what it does. But now you're saying you care about the code and review everything so I'm not sure what to make out o…

> My comment was based on you saying you don't care about the code and only what it does. But now you're saying you care about the code and review everything so I'm not sure what to make out of it.

I'm not the person you originally replied to, so my take is different, which explains your confusion :-)

However I do increasingly get the niggling sense I'm reviewing code out of habit rather than any specific benefit because I so rarely find something to change...

> And if you're really going too deep into the problem domain, what is the point of having the code abstracted?

Let's take my current work as an example: I'm doing stuff with computer vision (good old-fashioned OpenCV, because ML would be overkill for my case.) So the problem domain is now images and perception and retrieval, which is what I am learning and exploring. The actual code itself does not matter as much the high-level approach and the component algorithms and data structures -- none of which are individually novel BTW, but I believe I'm the only one combining them this way.

As an example, I give a high-level prompt like "Write a method that accepts a list of bounding boxes, find all overlapping ones, choose the ones with substantial overlap and consolidate them into a single box, and return all consolidated boxes. Write tests for this method." The AI runs off and generates dozens of lines of code -- including a tunable parameter to control "substantial overlap", set to a reasonable default -- the tests pass, and when I plug in the method, 99.9% of the times the code works as expected. And because this is vision-based I can immediately verify by sight if the approach works!

To me, the valuable part was coming up with that whole approach based on bounding boxes, which led to that prompt. The actual code in itself is not interesting because it is not a difficult problem, just a cumbersome one to handcode.

To solve the overall problem I have to combine a large number of such sub-problems, so the leverage that AI gives me is enormous.

Re: The highest quality codebase

#318

Post by 93n »

sfn42 wrote: post #273
breuleux wrote: post #261

Earlier quoted context omitted.

As someone who does that a lot... I agree. Self-indulgent is the word. It just feels great when the implementation is a perfect fit for your brain, but sometimes that's just not a good use of your time. Sometimes, you strike gold, so there's that.

I kind of struggle with this. I basically hate everyone elses code, and by that I mean I hate most people's code. A lot of people write awesome code but most people write what I'd call trash code. And I do think there's more to it than preference. Like there's actual bugs in the code, it's confusing and because it's confusing there's more bugs. It's solving a simple problem but doing so in an unnecessarily convoluted…

Yeah, I know this feeling very well.

I usually attribute it to people being lazy, not caring, or not using their brain.

It's quite frustrating when something is *so obviously* wrong, to the point that anyone with a modicum of experience should be able to realize that what was implemented is totally whack. Please, spend at least a few minutes reviewing your work so that I don't have to waste my time on nonsense.

Re: The highest quality codebase

#319

Post by keeda »

skydhash wrote: post #313
keeda wrote: post #300

Earlier quoted context omitted.

Note I'm not saying one is better than the other, but my takes: 1. The problem solving is in figuring out what to prompt, which includes correctly defining the problem, identifying a potential solution, designing an architecture, decomposing it into smaller tasks, and so on. Giving it a generic prompt like "build a fitness tracker" will result in a fully working product but it will be bland as it would be the average…

> The problem solving is in figuring out what to prompt, which includes correctly defining the problem, identifying a potential solution, designing an architecture, decomposing it into smaller tasks, and so on Coding is just a formal specification, one that is suited to be automatically executed by a dumb machine. The nice trick is that the basic semantics units from a programming language are versatile enough to giv…

I think you would be surprised by how much these AIs can "fill in the blanks" based on the surrounding code and high-level context! Here is an example I posted a few months ago (which is coincidentally, related to the reply I just gave the sibling comment): https://news.ycombinator.com/item?id=44892576

Look at the length of my prompt and the length of the code. And that's not even including the tests I had it generate. It made all the right assumptions, including specifying tunable optional parameters set to reasonable defaults and (redacted) integrating with some proprietary functions at the right places. It's like it read my mind!

Would you really think writing all that code by hand would have been comparable to writing the prompt?

Post reply on HN