You can get decent results from AI coding models, though…
…as long as somebody who actually knows how to program is directing it. Like if you tell it what inputs/outputs you want it can write a decent function - even going so far as to comment it along the way. I’ve gotten O1 to write some basic web apps with Node and HTML/CSS without having to hold its hand much. But we simply don’t have the training, resources, or data to get it to work on units larger than that. Ultimately it’d have to learn from large scale projects, and have the context size to be able to hold if not the entire project then significant chunks of it in context and that would require some very beefy hardware.
Generally only for small problems. Like things lower than 300 lines of code. And the problem generally can’t be a novel problem.
But that’s still pretty damn impressive for a machine.
But that’s still pretty damn impressive for a machine.
Yeah. I’m so dang cranky about all the overselling, that how cool I think this stuff is often gets lost.
300 lines of boring code from thin air is genuinely cool, and gives me more time to tear my hair out over deployment problems.
and only if you’re doing something that has been previously done and publically released
Well, not exactly. For example, for a game I was working on I asked an LLM for a mathematical formula to align 3D normals. Then I couldn’t decipher what it wrote so I just asked it to write the code for me to do it. I can understand it in its code form, and it slid into my game’s code just fine.
Yeah, it wasn’t seamless, but that’s the frustrating hype part of LLMs. They very much won’t replace an actual programmer. But for me, working as the sole developer who actually knows how to code but doesn’t know how to do much of the math a game requires? It’s a godsend. And I guess somewhere deep in some forum somebody’s written this exact formula as a code snippet, but I think it actually just converted the formula into code and that’s something quite useful.
I mean, I don’t think you and I disagree on the limits of LLMs here. Obviously that formula it pulled out was something published before, and of course I had to direct it. But it’s these emergent solutions you can draw out of it where I find the most use. But of course, you need to actually know what you’re doing both on the code side and when it comes to “talking” to the LLM, which is why it’s nowhere near useful enough to empower users to code anything with some level of complexity without a developer there to guide it.
If you know what you’re doing, AI is actually a massive help. You can make it do all the repetitive shit for you. You can also have it write the code and you either clean it or take the pieces that works for you. It saves soooooo much time and I freaking love it.
If you’re having to do repetitive shit, you might reconsider your approach.
Depending on the situation, repetitive shit might be unavoidable
Usually you can solve the issue by using regex, but regex can be difficult to work with as well
I’ve been trying to use aider for this, it seems really cool but my machine and wallet cannot handle the sheer volume of tokens it consumes.
I don’t even know what aider is. Lol. There are so many assistants out there. My company created a wrapper for chatgpt and gave us unlimited number of tokens and told us to go ham.
Aider is an LLM agent type app that has a programming assistant and an architect assistant.
You tell the architect what you want and it scans the structure of your code base to generate the boilerplate. Then the coder fills it in. It has command prompt access to then compile and run etc.
I haven’t really figured it out yet.
It’s taken me a while to learn how to use it and where it works best but I’m coming around to where it fits.
Just today i was doing a new project, i wrote a couple lines about what i needed and asked for a database schema. It looked about 80% right. Then asked for all the models for the ORM i wanted and it did that. Probably saved an hour of tedious typing.
I’m telling you. It’s fantastic for the boring and repetitive garbage. Databases? Oh hell yeah, it does really well on that, too. You have no idea how much I hate working with SQL. The ONLY thing it still struggles with so far is negative tests. For some reason, every single AI I’ve ever tried did good on positive tests, but just plain bad in the negative ones.
That’s the thing, it’s a useful assistant for an expert who will be able to verify any answers.
It’s a disaster for anyone who’s ignorant of the domain.
Tell me about it. I teach a python class. Super basic, super easy. Students are sometimes idiots, but if they follow the steps, most of them should be fine. Sometimes I get one who thinks they can just do everything with chatgpt. They’ll be working on their final assignment and they’ll ask me what a for loop is for. Than I look at their code and it looks like Sanscrit. They probably haven’t written a single line of code in those weeks.
I turned on copilot in VSCode for the first time this week. The results so far have been less than stellar. It’s batting about .100 in terms of completing code the way I intended. Now, people tell me it needs to learn your ways, so I’m going to give it a chance. But one thing it has done is replaced the normal auto-completion which showed you what sort of arguments a function takes with something that is sometimes dead wrong. Like the code will not even compile with the suggested args.
It also has a knack for making me forget what I was trying to do. It will show me something like the left side picture with a nice rail stretching off into the distance when I had intended it to turn, and then I can’t remember whether I wanted to go left or right? I guess it’s just something you need to adjust to. Like you need to have a thought fairly firmly in your mind before you begin typing so that you can react to the AI code in a reasonable way? It may occasionally be better than what you have it mind, but you need to keep the original idea in your head for comparison purposes. I’m not good at that yet.
I don’t mess with any of those in-IDE assistants. I find them very intrusive and they make me less efficient. So many suggestions pop up and I don’t like that, and like you said, I get confused. The only time I thought one of them (codium) was somewhat useful is when I asked it to make tests for the file I was on. It did get all the positive tests correct, but all the negative ones wrong. Lol. So, I naturally default to the AI in the browser.
Thanks, it makes me feel relieved to hear I’m not the only one finding it a little overwhelming! Previously, I had been using chatgpt and the like where I would be hunting for the answer to a particularly esoteric programming question. I’ve had a fair amount of success with that, though occasionally I would catch it in the act of contradicting itself, so I’ve learned you have to follow up on it a bit.
I haven’t personally used it, but my coworker said using Cursor with the newest Claude model is a gamechanger and he can’t go back anymore 🤷♂️ he hasn’t really liked anything outside of cursor yet
I knocked off an android app in Flutter/Dart/Supabase in about a week of evenings with Claude. I have never used Flutter before, but I know enough coding to fix things and give good instructions about what I want.
It would even debug my android test environment for me and wrote automated tests to debug the application, as well as spit out the compose files I needed to set up the Supabase docker container and SQL queries to prep the database and authentication backend.
That was using 3.5Sonnet, and from what I’ve seen of 3.7, it’s way better. I think it cost me about $20 in tokens. I’ve never used AI to code anything before, this was my first attempt. Pretty cool.
I used 3.7 on a project yesterday (refactoring to use a different library). I provided the documentation and examples in the initial context and it re-factored the code correctly. It took the agent about 20 minutes to complete the re-write and it took me about 2 hours to review the changes. It would have taken me the entire day to do the changes manually. The cost was about $10.
It was less successful when I attempted to YOLO the rest of my API credits by giving it a large project (using langchain to create an input device that uses local AI to dictate as if it were a keyboard). Some parts of the codes are correct, the langchain stuff is setup as I would expect. Other parts are simply incorrect and unworkable. It’s assuming that it can bind global hotkeys in Wayland, configuration required editing python files instead of pulling from a configuration file, it created install scripts instead of PKGBUILDs, etcetc.
I liken it to having an eager newbie. It doesn’t know much, makes simple mistakes, but it can handle some busy work provided that it is supervised.
I’m less worried about AI taking my job then my job turning into being a middle-manager for AI teams.
I think the further you get out in to esoteric or new things, the less they have to draw on. I’ve had a bit of the same issue building Lora telemetry on ESP32 with specific radio modules because there might be a couple of realworld examples out there of using those libraries.
It depends. AI can help writing good code. Or it can write bad code. It depends on the developer’s goals.
LLMs can be great for translating pseudo code into real code or creating boiler plate or automating tedious stuff, but ChatGPT is terrible at actual software engineering.
It depends. AI can help writing good code. Or it can write bad code
I’ll give you a hypothetical: a company is to hire someone for coding. They can either hire someone who writes clean code for $20/h, or someone who writes dirty but functioning code using AI for $10/h. What will many companies do?
Many companies chose cheap coders over good coders, even without AI. Companies I heard of have pretty bad code bases, and they don’t use AI for software development. Even my company preferred cheap coders and fast development, and the code base from that time is terrible, because our management didn’t know what good code is and why it’s important. For such companies, AI can make development even faster, and I doubt code quality will suffer.
And of course the ai put rail signals in the middle.
Chain in, rail out. Always
!Factorio/Create mod reference if anyone is interested !<
The key is identifying how to use these tools and when.
Local models like Qwen are a good example of how these can be used, privately, to automate a bunch of repetitive non-determistic tasks. However, they can spot out some crap when used mindlessly.
They are great for skett hing out software ideas though, ie try a 20 prompts for 4 versions, get some ideas and then move over to implementation.
