[_8j50]

I feel like such a jerk for not wanting to use chatgpt for all that. It's not just mild paranoia about feeding it input I prefer be kept private but I just don't enjoy having someone else do half the thinking for me I guess.

I mean, I don't like intellisense either (but simple autocomplete is fine). Perhaps it is because I only code to help with my job, I don't get paid to have a lot of good quality code output.

[sanderjd]

I think I would have felt this way when I was younger. But after writing code for over twenty years, I'm very happy to let computers do the boring half of the thinking, so that I can think about more interesting things.

It is not intellectually stimulating for me to think about what the syntax for a dict comprehension is, or what exactly I'm supposed to do to map over the values of an array in javascript without screwing it up, or any of a million other kinds of minutia. Computers know the answers to these uninteresting questions.

[shanusmagnus]

That's what's been so striking for me -- the stuff that is fun and playful for me I get to do; and a bunch of stuff that I hated I can now offload, with the net result that I get to work at the level of abstraction that is most interesting and most human, vs acting like a human robot trying to unearth documentation, API examples, etc.

There's no question about this being the right way to use it for me, but I wonder if this could introduce something bad for someone just starting out, who hadn't first got all the reps with the drudgery over decades? Still mulling on that.

[sanderjd]

Yeah, I've said a bunch that I'm worried about people starting out from scratch. So much of what I do after I get responses from LLMs is best described as "taste", but how would I have developed that taste without the years of slogging through?

But I also think this is probably just a classic geezer's concern about kids being on my lawn, and it will probably work out just fine for these youths :)

[jprete]

Eh. I think the peak of computer ability was GenX. I’m not in that group but made up for it with sheer intensity. If you grow up on a phone you’re not getting any of the mental modeling to get close to what the machine is doing and you’re only going to be able to work with the limited tools of that level until you deliberately dive deeper.

[shanusmagnus]

I think both you and the GP are onto something important. I am one of the vaunted Gen-Xers (this is the first time someone has said anything nice about us, so thanks) and there is something to the idea that my understanding of systems goes down to assembly language (fully) and even CPU architecture (very sketchily) all the way up to, like, web frameworks. So for the stuff I'm usually doing, I understand several layers up and down, and that often seems valuable.

This strikes me as the essence of expertise, the difference between talking to someone who's read a book or a review paper, vs someone who is a real expert at that thing. You can be quite competent and insightful from having done a modest amount of reading and thinking, but if you're seeing the Matrix, and know how all these forces are interacting with each other, that's just a whole other level. It makes an impression when you brush up against it.

However: it always weighs on me how this is all a matter of framing. Like, I don't know the electronics. There's a level of metal that I don't get. Some of the really high-level stuff is now beyond me, too. I catch myself saying "I should really take x {weeks, months, years} and really grok that." And yet my actual experience suggests this is a mirage.

More briefly: there are always more layers for a fuller understanding. It's hard to see how many of them are really useful. Maybe the kid who is 10x better than me at LLM collaboration will benefit more than from having a deeper stack. It's interesting to ponder how these different consequences will play out.

[sanderjd]

FWIW I'm a (geriatric) millennial, and we were totally taught all that same stuff. And yeah, it totally feels important to me to have this mental model up and down the layers. But I also do wonder whether we're just wrong about that, merely falling prey to nostalgia.

My messy answer is that for many projects it's either neutral or an actual hindrance - I have to remind myself to pragmatically not care about stuff that won't matter for years at the project's expected growth rate - but for other projects it's very useful. I think the way to go is to seek out those kinds of projects, in order to avoid frustration all around.

[jprete]

I think a lot of the drudgery is lack of language quality. But this is still a better argument than I’ve seen before for using it.

[sanderjd]

I dunno, I've used all kinds of languages, from the ones people often consider lower quality to the ones people often consider higher quality, and they all have something like this.

And maybe there's some as yet unexplored design space out there for which this isn't true, but my prior is that we're actually just circling around some essential complexity at the core of the problem, which will never be eliminated.

[breckenedge]

It takes programming back to the pseudocode experience, but now the computer can fill in all the code bits really well about 75% of the time

[sanderjd]

Yeah, 75% seems a bit high, but it's a high enough percentage to be extremely useful to me.

[n4r9]

Don't beat yourself up. As a mathematically-oriented software engineer I also have little to no interest in using LLMs to help with coding. It feels like the people that do are the builders, i.e. interested in quickly knocking up something that works most of the time. Which is great from a business perspective. I can't help but see my programming output as an artistic expression of my thought, and therefore find it difficult to give up the hands-on construction to others (be it LLMs or juniors).

[sanderjd]

I think the division is along a different axis than this one (or probably it's along multiple axes).

I've always been more of a fastidious crafter than a "just get it built" person, but I also struggle with a blank page. I thrive on editing more than writing. Since forever, I like to get out something that works or mostly works, and then start carving on it until I like it.

LLMs have been helping me get some ink on the page, but very little of what they suggest ends up in the final product.

[jprete]

I’ve observed for a long time that there’s a lot of value in making a seed, a starting point, for the thing a group needs to create. And that’s exactly the reason - new text is harder than criticism of the old.

[sanderjd]

Yep! But some people do seem to thrive more with a blank page.

Supposedly Tom Robbins writes books entirely by putting one word after another starting with the first one and finishing with the last one. I don't know if that's apocryphal, but I do think that's closer to the process for some people.

But if I were a writer, I'd be squarely in the "get out a first draft, it will be like pulling teeth, but just get something down; then you can do the fun part of revising and polishing".

[corethree]

Mathematically oriented software engineers have the most to benefit off of software assistance due to algebraic designs.

As one myself LLMs don't feel like giving up control it feels like collaboration. You probably don't like collaboration.

[jprete]

Claiming that someone doesn’t like collaboration because they don’t want to use ChatGPT is a very unreasonable and biased take.

[bumbledraven]

Not especially more biased than GGP's claim that people who use LLMs as coding assistants are "builders, i.e. interested in quickly knocking up something that works most of the time".

[n4r9]

Could you expand on the comment about "algebraic designs"?

When I interact with an LLM it feels like I'm speaking to someone who lacks inherent conceptual understanding, but is doing their utmost best to bullshit me. This is problematic when it comes to algorithmic thinking.

I sometimes need to solve problems that involve tweaking existing algorithms in somewhat novel ways. For example "k-medoid clustering but with various capacity constraints on clusters", or "contraction heirarchies but accounting for varying vehicle dimension restrictions".

I love collaborating with smart colleagues to come up with ideas to solve these problems. Seeing chat-gpt fail to solve very simple traveling salesman type problems gives me little confidence that it can do novel conceptual tihnking.

EDIT

To test my own claims, I just tried asking Chat-GPT to make this modification to k-means clustering. It produced something that will give a result but will likely not be very optimal. When prompted to refine the solution, it failed to understand the issue and instead proposed the exact same solution just with a bit more implementation detail.

User

Suggest a modification to the k-means algorithm where the number of elements assigned to each cluster is limited to a pre-defined maximum value.

ChatGPT

To modify the traditional k-means algorithm to limit the number of elements assigned to each cluster to a pre-defined maximum value, you can create a variation of k-means called "k-means with cluster size constraints." This modification ensures that no cluster exceeds the specified maximum size while still optimizing cluster centroids based on the sum of squared distances. Here's a high-level overview of the modified algorithm:

1 Initialize centroids: Start by randomly selecting K initial centroids, where K is the desired number of clusters.

2 Assign data points to clusters: Assign each data point to the nearest centroid based on Euclidean distance, just like in the traditional k-means algorithm.

3 Update centroids: Recalculate the centroids of each cluster by taking the mean of all the data points assigned to that cluster.

4 Check cluster sizes: After updating the centroids, check the size of each cluster. If any cluster exceeds the pre-defined maximum size, proceed to reassign some data points from that cluster to other clusters. Here's how you can do this: Identify the cluster(s) that exceed the maximum size. For each over-sized cluster: Sort the data points in that cluster by their distance to the cluster centroid in ascending order. Start reassigning the farthest data points to other clusters (the ones with the smallest distances) until the cluster size constraint is satisfied. Update the centroids of the affected clusters accordingly.

5 Repeat steps 2 and 3: Continue iterating between data point assignment and centroid updating until convergence, or until a predefined number of iterations have been reached.

6 Termination: The algorithm terminates when either the cluster assignments do not change significantly between iterations or after a fixed number of iterations.

Here are a few things to consider when implementing this modification:

    You will need to experiment with the order in which you reassign data points from over-sized clusters to minimize the impact on the overall clustering quality.

    You should set an appropriate stopping criterion to prevent the algorithm from running indefinitely.

    Be prepared to handle situations where it is impossible to meet the cluster size constraint while maintaining good cluster quality. In such cases, you may need to relax the constraint or consider alternative clustering methods.

This modified k-means algorithm with cluster size constraints allows you to control cluster sizes while still finding meaningful clusters in your data.

User

Your proposed solution has an issue that points might be reassigned even if there are clearly no other suitable clusters. Please tweak the solution to avoid this issue.

ChatGPT

To address the issue of potentially reassigning points even when there are no other suitable clusters, we can modify the approach by introducing a priority queue or heap data structure to efficiently manage the reassignment process. Here's an improved version of the k-means algorithm with cluster size constraints:

1 Initialize centroids: Start by randomly selecting K initial centroids, where K is the desired number of clusters.

2 Assign data points to clusters: Assign each data point to the nearest centroid based on Euclidean distance, just like in the traditional k-means algorithm.

3 Update centroids: Recalculate the centroids of each cluster by taking the mean of all the data points assigned to that cluster.

4 Check cluster sizes: After updating the centroids, check the size of each cluster. If any cluster exceeds the pre-defined maximum size, proceed to reassign data points from that cluster to other clusters. Here's how you can do this: Identify the cluster(s) that exceed the maximum size. For each over-sized cluster: Create a priority queue (or heap) to store the data points in the cluster, ordered by their distance to the cluster centroid in ascending order. Start reassigning the farthest data points to other clusters (the ones with the smallest distances) until the cluster size constraint is satisfied. Update the centroids of the affected clusters accordingly. Continue this process until either the cluster size constraint is met or there are no more suitable clusters to reassign points to.

5 Repeat steps 2 and 3: Continue iterating between data point assignment and centroid updating until convergence, or until a predefined number of iterations have been reached.

6 Termination: The algorithm terminates when either the cluster assignments do not change significantly between iterations or after a fixed number of iterations.

This modified approach ensures that points are only reassigned to clusters that are suitable and have room to accommodate additional points while maintaining the overall quality of the clustering solution. The use of a priority queue helps prioritize the reassignment of points to clusters with the least impact on their quality.

Additionally, you should set an appropriate stopping criterion to prevent the algorithm from running indefinitely, and you may need to handle situations where it is impossible to meet the cluster size constraint while maintaining good cluster quality by relaxing the constraint or considering alternative clustering methods.

[corethree]

How is what you're doing mathematical? I mean you can call CS "math", but then I don't know what you mean by more "mathematical." Traditional cs algos are not what I term as more mathy from my pov. Maybe you can call stats "mathy" but this is more applied math and not too different from what "builders" do.

Also what you're doing here is asking chatGPT for the answer. chatGPT is more effective via collaboration. Meaning instead of shoving the entire problem down it's throat and asking it to solve it, you ask it for advice. Ask it for bits and pieces of things.

[n4r9]

To some extent I agree with you, in that all software engineers have to think about refactoring and time complexity, involving a logical or mathematical style of thinking. However, there's definitely a spectrum of how distinctly mathematical the work of a software engineer is.

A lot of front-end development for example does not require familiarity with any algorithms, formulae or mathematical structures. You might need to reason about large systems and have a rough idea of when hashmaps are useful, but the bulk of the work is constructing an interface according to functional business requirements. I frequently see comments here along the lines of "why am I being interviewed about algorithms when I'll never use them in my job".

A more mathematically oriented developer may be in the business of modelling and predictions. They may be confronted with a novel real world problem involving traffic, or trading, or electricity networks, that potentially no one has tried to solve before. They may be required to find a mathematical structure that closely approximates real world behaviour, implement that structure via code, and deploy a continuous model which allows their client to analyse and project.

Of course, you also have academic mathematicians using software like Maple or SageMath to assist with their research. This is another level more mathematical. Perhaps what you're getting at is that people can ask ChatGPT questions like "write me some Sage code to get the Delaunay triangulation of this set of points". I totally agree that it can probably do well at these tasks.

[corethree]

Modelling stuff sounds like data science. It's a term they often use and it sounds very much like the same deliverables you mentioned. I've never seen a data scientist term themselves as more mathematically oriented. Also let's not play around, what you actually meant to say mathematically "superior". That much is clear. Sounds like you know stats and you think that makes you more "mathematical".

You also talk about things like traffic. Modelling traffic is mathematical? Sounds like a simulation to me. Man take a look at GTA. That game is almost entirely made by builder engineers creating simulations. It's the same shit and likely far more advanced then what any data scientist can come up with.

Anyway from your example and from what Ive seen it sounds like you're still doing the same thing. CS algorithms. You're just using algorithms that aren't likely very popular or very specific to data and stats. But adjusting stuff like k-means clustering still sounds like regular cs stuff to me.

There's no point in calling it more "mathematical" because it's not. The builder engineer who wrote all the systems in GTA or even say red dead redemption use a ton of "math" even and they don't term themselves more "mathematical" even though their simulations are likely more complex than anything you will ever build.

That's why when you called your self mathematically superior (again don't deny this.. we all know what you really mean here) I thought you were talking actual math. Because if you looked at a math equation it doesn't look anything like an algorithm. Math equations are written as a single expression. Math equations model the world according to a series of formula. It's very different to a cs algorithm.

Mathematical oriented programming involves largely the same thing and using algebras of mathematics.

If you're not doing this just call it data science instead of trying to call yourself more "mathematical". If you truly were more mathematically oriented you would know what I'm talking about.

Geeze some guy writing "models" and doing some applied math+stats like what every other freaking programmer out there is doing and he calls himself more "mathematically oriented."

[bumbledraven]

An LLM is going to be most helpful for topics that came up a lot during training. What you're discussing doesn't sound like it falls into that category.

[n4r9]

I'd agree with that. I'd even go a step further and say that most of my work and things I'm interested in coding don't fall into that category. I have absolutely nothing against people who do find it useful, but I'm keen to reassure user badrabbit that they're not a jerk for not being interested in using LLMS.

[deelly]

I know exactly why I don't want to use ChatGPT.

I love to write code, I love to modify existing code too.

I do not love to read and then fix code after someone all the time. With ChatGPT I have to read then understand then fix code after ChatGPT every time.

Also, I do not love to fix code that often contains hallucination.

[bumbledraven]

First, are you sure using GPT-4?

Second, have you tried pasting any syntax errors you get back into the chat window? Usually, GPT will try to fix them.

Third, you can have GPT write a function for you and then write a different version of the function using a different algorithm along with a test (e.g. a fuzz test) to check whether two functions produce the same output given the same input. This makes it less likely that an error will slip through because both algorithms would have to be produce the same incorrect output for the same input.

[deelly]

Yes, I used chatGPT-4.

Second, your fix is to verify code generated by LLM and then play with it trying to find a way to fix it. I`m quite sure that I will spend less time and less mental power by writing code in the first place.

Third fix is to play with chatGPT more, and read more code generated by chatGPT trying to find errors in it.

What happened with "reading code written by someone else is harder than writing your own code"?