Just learn how to code

[At30wecashout]

Coding is hard. I tried but not for me . Screw you python lol

man and help. But I agree

 

[IIVI]

Exactly, the same thing as Generative AI for artwork, if you can draw or paint, 3d Model etc... (digital art), you will be 100% more efficient than someone who can't.

Same thing with Generative AI for code, knowing how to code puts you 100% above those who don't.

I can draw, paint, 3d model and code(multiple languages) etc..., generative AI is like "Cloning" yourself a dozen times, and working together to get tasks done.

Even understanding code(or art) will let you better properly construct a prompt to get the best results from the AI.

---

For those who don't know how to code, take some time out and learn the fundamentals (Variables, Assignment, Conditional Logic, Functions, Using Objects Etc...).

Once you learn the basics, then it opens the doors to use basically any language, as you would only have to really the intricacies of the particular syntax.

There are many free resources online (YouTube Especially) to learn the basics of any programming language you want.

Yup. Look at the edit I made to my post.

Now if you’re an artists you can make small spot changes to a drawing and get it exactly the way you want, without the risk of making changes to any other part of the drawing.

Same goes for coding. Don’t know how many times I had to tell A.I not to touch “this part of the code” or “keep this code the same, but add __ to it” and it ignores me and does a monster rewrite.

It’s great for large scale work, it when things get intricate it can be a pain, especially if you more not an expert.

 

[Dameon Farrow]

You should still learn. Using AI will screw you in the end if you aren't big on how to actually use the language itself. Everything will be fine until you have a mid sized project full of issues and AI spoiled you into thinking all the solutions are a click away. You'll wanna hire somebody.

Apart from that? And this is something the influencers refuse to discuss.....

There is still billions of lines of code out there that was written pre AI that will need to be maintained. AI is not about to simply update all that to some flashy new language.

Stop letting these influencers scare you. Learn this shyt. And go get some kind of degree in it.

 

[Elim Garak]

I mean we knew this was coming already.

 

[BlackMajik]

You should still learn.

Yeah learn for yourself...not to get a job

 

[Braman]

Friendly reminder: “You won’t be replaced by AI. You will be replaced by someone using AI”

 

[bnew]

Vibe Coding with Cursor Pro to me was a game changer. Like I said before I got months of work done in a few hours because I’m familiar with the codebase structure, product and edge cases.

I don’t think something like this, especially for large products with a lot of edge cases is as useful if it’s not showing the code. It may be great for quick one-off apps, but would probably be inconsistent when you want to expand functionality at a later point.

That’s always the challenge with A.I: keeping long term context.

So many times it got to keep re-doing on spot analysis and that’s why stuff like this happens:

I actually ask the LLM to account for edge cases and I also ask it to show me examples of badly formatted outputs the code could produce and solutions to prevent it.

you don't need to start a new chat after each edit, depending on the model or how many characters/lines of code you're working with you may need to start a new chat after 10 or so edits but you can just instruct the model to keep the current code structure or just send the latest code in full in chat. i have very long conversations where the final code is largely the same except for specific changes i requested.

 

[tuckgod]

I think at most, it lowers the barrier to entry to (in this case) making interactive designs. A glorified wizard.

It’s over bud

 

[bnew]

@Voice of Reason

whats so funny?

I've posted lots of A.I generated code on here as evidence of what's possible.

i'm not a coder and it's been amazing.

 

[IIVI]

I actually ask the LLM to account for edge cases and I also ask it to show me examples of badly formatted outputs the code could produce and solutions to prevent it.

you don't need to start a new chat after each edit, depending on the model or how many characters/lines of code you're working with you may need to start a new chat after 10 or so edits but you can just instruct the model to keep the current code structure or just send the latest code in full in chat. i have very long conversations where the final code is largely the same except for specific changes i requested.

I’ve personally noticed the code start to drift in implementation as it never tends to keep the same styling/formatting or “tone”/vocabulary over time. It does some subtle things that are different from month to month. Like why did it all of a sudden start changing naming formats? There are some “black swans” it tends to pull out of nowhere despite telling it to not make changes. It’ll change something, then you got to tell it to not change that from now on.

That’s only for personal projects. Now imagine multiple teams working on different parts of the codebase on projects with 5-10+ million lines of code meant to keep infrastructures running and working with each other. We’re not even talking the mega codebases. You want humans to be monitoring stuff like that (it’s fine for A.I to write it, but human professionals need to verify and have test cases). Blindingly trusting an A.I for that is asking for a lot of death. I’ve seen these things mess up a fair amount if nested else if and modular logic to be very thorough double checking the output.

I like it as a tool right now for small to moderate complex coding, but I’ve had a good amount of mixed experiences as well.

 

[CopiousX]

meh, nothing spectacular.

What about databases, image storage, rest apis, authentication, 3rd party integration etc. I'm sure AI will get there but this isn't anything different from other AI platforms. I can ask Claude or Chatgpt to do the same thing.

I'm still convinced they have real flesh and blood Indians on the other side of the planet verifying these prompts for their companies . Silicon valley is notorious for their grifts



And then they feed this to the shareholders telling them they don't need anymore developers, while their whole infrastructure is falling apart

 

[MikelArteta]

the crazy thing this is like a iphone 3 camera compared now. Yeah ai cant do this and that but in ten years

 

[null]

That’s always the challenge with A.I: keeping long term context.

relative context too (which requires understanding / problem solving skills).

e.g. some things which you say are more important than others. main trunk inputs are different to adjunct inputs.

stuff like that.

 

[null]

the crazy thing this is like a iphone 3 camera compared now. Yeah ai cant do this and that but in ten years

ten years what? computers cannot and will not understand turing machine based programs within the next 10 years. if ever.

if they get that far then its not just programmers who need to look out.

 

[TheMailMan]

Big respect for keeping it real but look at it this way: it’s way more lucrative to learn something hard than something average people can learn easy. U want to specialize in whatever field u choose.

Spoiler

which is why I say learn hvac or plumbing while you’re young

That's why I drive a truck lol