I don’t know what I do differently, but I can get Cursor to do exactly what I want all the time.
Maybe it’s because it takes more time and effort, and I don’t connect to GitHub or actual databases, nor do I allow it to run terminal commands 99% of the time.
I have instructions for it to write up readme files of everything I need to know about what it has done. I’ve provided instructions and created an allow list of commands so it creates local backups of files before it touches them, and I always proceed through a plan process for any task that is slightly more complicated, followed by plan cleanup, and execution. I’m super specific about my tech stack and coding expectations too. Tests can be hard to prompt, I’ll sometimes just write those up by hand.
Also, I’ve never had to pay over my $60 a month pro plan price tag. I can’t figure out how others are even doing this.
At any rate, I think the problem appears to be the blind commands of “make this thing, make it good, no bugs” and “this broke. Fix!” I kid you not, I see this all the time with devs. Not at all saying this is what you do, just saying it’s out there.
And “high quality code” doesn’t actually mean anything. You have to define what that means to you. Good code to me may be slop to you, but who knows unless it is defined.
When it comes to games I absolutely don’t care what they used AI for because the point of games is to be fun.
If it’s fun and you used AI, that’s fine with me. The game served its purpose.
The line for me is copyright on images. If you use ai to generate images to copy a popular game art style, I think that’s over the line. Create your own art or pay the artist.
Code however, I see it as a tool. You wouldn’t scold me for hiring a cheap programmer to get the work done. So to me, AI for coding isn’t any different than hiring a programmer to do the work for you. No problem there.
That being said, I do game dev, and using AI to help figure out an algorithm or do the work of creating my inputs code, etc is a big time saver. However, at the moment, it really struggles with anything else because it has no vision and explaining to it how to put code together for a weird game mechanic or level generation reminds me of that game where you explain how to make a peanut butter and jelly sandwich in the 3rd grade, and you tell your teacher to put the peanut butter on the bread and she scoops it out with her hand…
> You wouldn’t scold me for hiring a cheap programmer to get the work done.
It’s literally the same. There is no difference, either you acknowledge AI is potentially a useful tool to lower costs of development (especially important for indie devs) or it’s exploitative and puts both artists and programmers out of a job.
There’s plenty of things in the art workflow that can be automated same as code, pay an artist to do key frames/storyboarding and use the AI to animate between them? Is this exploitative?
EDIT: I’m reminded of this thread from 2019 about a successful game dev that admits their games look like shit due to cheaping out on art: https://news.ycombinator.com/item?id=20804998
It's a real shame its raster functionality wasn't integrated into Illustrator. Adobe really butchered the whole Macromedia portfolio, didn't they?
(For those unfamiliar, Illustrator is a pure vector graphics editor; once you rasterize its shapes, they become uneditable fixed bitmaps. Fireworks was a vector graphics editor that rendered at a constant DPI, so it basically let you edit raster bitmaps like they were vectors. It was invaluable for pixel-perfect graphic design. Nothing since lets you do that, though with high-DPI screens and resolution-independent UIs being the norm these days, this functionality is less relevant than it used to be.)
At my last job m our designer was a Fireworks holdout. It was very pleasant. As someone who has to implement UIs, I greatly preferred it to Figma, though with today's flat boring designs there's a lot less slicing.
I feel like I can't really have fun and be myself when I see people shooting video all around me.
I like to be silly with my kids and close friends, I like to act out around the people who find me fun or funny. But the rest of the world would ridicule me, or make fun of me, or make me a meme possibly.
This makes me sad because as a young man I could just be out there and fun, and at the end of the day, I held a place in the memories of my closest friends, maybe a handful of bystanders. But today, I could be gif'd and immortalized for my silly actions without my permission.
I disagree with the sentiment, you're in public, it's fair game. That just means I have to bend to your world-view, and you don't have to be considerate of mine.
This article is just simply not true for most people who have figured out how to use AI properly when coding. Since switching to Cursor, my coding speed and efficiency has probably increased 10x conservatively. When I'm using it to code in languages I've used for 25+ years, it's a breeze to look over the function it just saved me time by pre-thinking and typing it out for me. Could I have done it myself, yeah, but it would have taken longer if I even had to go lookup one tiny thing in the documentation, like order of parameters for a function, or that little syntax thing I never use...
Also, the auto-complete with tools like Cursor are mind blowing. When I can press tab to have it finish the next 4 lines of a prepared statement, or it just knows the next 5 variables I need to define because I just set up a function that will use them.... that's a huge time saver when you add it all up.
My policy is simple, don't put anything AI creates into production if you don't understand what it's doing. Essentially, I use it for speed and efficiency, not to fill in where I don't know at all what I'm doing.
What do you even mean with a 10x increase in efficiency? Does that means you commit 10x more code every day? Or that "you" essentially "type" code 10x faster? In the later case all the other tasks surrounding code would still take around the same netting you much less than 10x increase in overall productivity, probably less than 2x?
My favorite example, and the ones I show my team and my employer, is that I can have AI look at a string of fields for my database table and generate all the views for the display, add, and edit forms for those fields in exactly the way I instruct, and that saves me as much as 30 minutes every time I do it. If I do this 8 times in a day, that would save me about 4 hours. Especially when those forms require things like lookups and extra JavaScript functionality.
Another great example, is the power of tabbing with Cursor. If I want to change the parameters of a function in my React app, I can be at one of the functions anywhere in my screen, add a variable that relates to what is being rendered, and I can now quickly tab through to find all the spots that also are affected in that screen, and then it usually helps apply the changes to the function. It's like smart search and replace where I can see every change that needs made but it knows how to make it more intelligently than just replacing a line of code - and I didn't have to write the regex to find it, AND it usually helps get the work done in the function as well to reflect the change. That could save me 3-5 minutes, and I could do that 5 times a day maybe, and another almost half-hour is saved.
The point is, these small things add up SO fast. Now I'm incredibly efficient because the tedious part of programming has been sped up so much.
I have a $20/month GPT subscription, and the $20/month cursor plan. I've yet to come close to going over my limits with either service. I use the unlimited Tab completions in cursor which are what end up saving me an enormous amount of time. I probably use 5 to maybe 10 chats a day in cursor, but I jump over to GPT if I think I'm going to require a few extra chats to get to the bottom of something.
I think that getting "good" at using AI means that you figure out exactly how to formulate your prompts so that the results are what you are looking for given your code base. It also means knowing when to start new chats, and when to have it focus on very specific pieces of code, and finally, knowing what it's really bad at doing.
For example, if I need to have it take a list of 20 fields and create the HTML view for the form, it can do it in a few seconds, and I know to tell it, for example, to use Bootstrap, Bootstrap icons, Bootstrap modals, responsive rows and columns, and I may want certain fields aligned certain ways, buttons in certain places for later, etc, and then I have a form - and just saved myself probably 30 minutes of typing it out and testing the alignment etc. If I do things like this 8 times a day, that's 4 hours of saved time, which is game changing for me.
I am currently subscribed to Claude Pro, which is $20/mo and gives you plenty to experiment with by giving you access to Projects and MCP in Claude Desktop and also Claude Code for a flat monthly fee. (I think there are usage limits but I haven't hit them).
I've probably fed $100 in API tokens into the OpenAI and Anthropic consoles over the last two years or so.
I was subscribed to Cursor for a while too, though I'm kinda souring on it and looking at other options.
At one point I had a ChatGPT pro sub, I have found Claude more valuable lately. Same goes for Gemini, I think it's pretty good but I haven't felt compelled to pay for it.
I guess my overall point is you don't have to break the bank to try this stuff out. Shell out the $20 for a month, cancel immediately, and if you miss it when it expires, resub. $20 is frankly a very low bar to clear - if it's making me even 1% more productive, $20 is an easy win.
This is really interesting, got it up and running very quickly.
I'm not sure what the use case is and it doesn't auto-load chromium with its own web server from what I can tell. Is it just for creating javascript CLI utilities?
Wild West Domains is a subsidiary of GoDaddy. They are basically he same company, and the Whois doesn't usually show the owner of the domain anymore, it shows the company that's keeping the owner's information private. WWD and GoDaddy both offer this service. Lookup other domains, you'll see the same thing all over the place. The whois on just about all of my domains say Wild West Domains, the others are GoDaddy or Namecheap, my personal information never comes up anymore because I opt for the privacy options.
Emacs has completion preview mode, which shows the completion inline in grey text. This is what I prefer using at it does not block text, and I am only interested in the top completion 99% of the time.
There was some shitty IDE years ago that would stop your keyboard input because it clogged the CPU with lookups for auto complete. It might have been eclipse or some other java monstrosity.
I don’t know what I do differently, but I can get Cursor to do exactly what I want all the time.
Maybe it’s because it takes more time and effort, and I don’t connect to GitHub or actual databases, nor do I allow it to run terminal commands 99% of the time.
I have instructions for it to write up readme files of everything I need to know about what it has done. I’ve provided instructions and created an allow list of commands so it creates local backups of files before it touches them, and I always proceed through a plan process for any task that is slightly more complicated, followed by plan cleanup, and execution. I’m super specific about my tech stack and coding expectations too. Tests can be hard to prompt, I’ll sometimes just write those up by hand.
Also, I’ve never had to pay over my $60 a month pro plan price tag. I can’t figure out how others are even doing this.
At any rate, I think the problem appears to be the blind commands of “make this thing, make it good, no bugs” and “this broke. Fix!” I kid you not, I see this all the time with devs. Not at all saying this is what you do, just saying it’s out there.
And “high quality code” doesn’t actually mean anything. You have to define what that means to you. Good code to me may be slop to you, but who knows unless it is defined.