[dingnuts]

> You might prefer manual coding, but you might just be bad at AI coding and you might prefer it if you improved at it.

ok but how much am I supposed to spend before I supposedly just "get good"? Because based on the free trials and the pocket change I've spent, I don't consider the ROI worth it.

[qinsig]

Avoid using agents that can just blow through money (cline, roocode, claudecode with API key, etc).

Instead you can get comfortable prompting and managing context with aider.

Or you can use claude code with a pro subscription for a fair amount of usage.

I agree that seeing the tools just waste several dollars to just make a mess you need to discard is frustrating.

[goalieca]

And how often do your prompting skills change as the models evolve.

[badsectoracula]

It wont be the hippest of solutions, but you can use something like Devstral Small with a full open source setup to get experimenting with local LLMs and a bunch of tools - or just chat with it with a chat interface. I did pingponged between Devstral running as a chat interface and my regular text editor some time ago to make a toy project of a raytracer [0] (output) [1] (code).

While it wasn't the fanciest integration (nor the best of codegen), it was good enough to "get going" (the loop was to ask the LLM do something, then me do something else in the background, then fix and merge the changed it did - even though i often had to fix stuff[2], sometimes it was less of a hassle than if i had to start from scratch[3]).

It can give you a vague idea that with more dedicated tooling (i.e. something that does automatically what you'd do by hand[4]) you could do more interesting things (combining with some sort of LSP functionality to pass function bodies to the LLM would also help), though personally i'm not a fan of the "dedicated editor" that seems to be used and i think something more LSP-like (especially if it can also work with existing LSPs) would be neat.

IMO it can be useful for a bunch of boilerplate-y or boring work. The biggest issue i can see is that the context is too small to include everything (imagine, e.g., throwing the entire Blender source code in an LLM which i don't think even the largest of cloud-hosted LLMs can handle) so there needs to be some external way to store stuff dynamically but also the LLM to know that external stuff are available, look them up and store stuff if needed. Not sure how exactly that'd work though to the extent where you could -say- open up a random Blender source code file, point to a function, ask the LLM to make a modification, have it reuse any existing functions in the codebase where appropriate (without you pointing them out) and then, if needed, have the LLM also update the code where the function you modified is used (e.g. if you added/removed some argument or changed the semantics of its use).

[0] https://i.imgur.com/FevOm0o.png

[1] https://app.filen.io/#/d/e05ae468-6741-453c-a18d-e83dcc3de92...

[2] e.g. when i asked it to implement a BVH to speed up things it made something that wasn't hierarchical and actually slowed down things

[3] the code it produced for [2] was fixable to do a simple BVH

[4] i tried a larger project and wrote a script that `cat`ed and `xclip`ed a bunch of header files to pass to the LLM so it knows the available functions and each function had a single line comment about what it does - when the LLM wrote new functions it also added that comment. 99% of these oneliner comments were written by the LLM actually.

[grogenaut]

how much time did you spend learning your last language to become comfortable with it?

[stray]

You're going to spend a little over $1k to ramp up your skills with AI-aided coding. It's dirt cheap in the grand scheme of things.

[viraptor]

Not even close. I'm still under $100, creating full apps. Stick to reasonable models and you can achieve and learn a lot. You don't need latest and greatest in max mode (or whatever the new one calls it) for majority of the tasks. You can have to throw the whole project at the service every time either.

[viraptor]

Typo: ...you don't have to throw the whole project context...

[dingnuts]

do I get a refund if I spend a grand and I'm still not convinced? at some point I'm going to start lying to myself to justify the cost and I don't know how much y'all earn but $1k is getting close

[theoreticalmal]

Would you ask for a refund from a university class if you didn’t get a job or skill from it? Investing in a potential skill is a risk and carries an opportunity cost, that’s part of what makes it a risk

[HDThoreaun]

No one is forcing you to improve. If you don’t want to invest in yourself that is fine, you’ll just be left behind.

[asciimov]

How are those without that kind of scratch supposed to keep up with those that do?

[theoreticalmal]

This kind of seems like asking “how are poor people supposed to keep up with rich people” which we seem to not have a long term viable answer for right now

[wiseowise]

What makes you think those without that kind of scratch are supposed to keep up?

[asciimov]

For the past 10 years we have been telling everyone learn to code, now it’s learn to build AI prompts.

Before a poor kid with a computer access could learn to code nearly for free, but if it costs $1k just to get started with AI that poor kid will never have that opportunity.

[wiseowise]

For the past 10 years scammers and profiteers been telling everyone to learn to code, not we.

[throwawaysleep]

If you lack "that kind of scratch", you are at the learning stage for software development, not the keeping up stage. Either that or horribly underpaid.

[bevr1337]

I recently had a coworker tell me he liked his last workplace because "we all spoke the same language." It was incredible how much he revealed about himself with what he thought was a simple fact about engineer culture. Your comment reminds me of that exchange.

- Employers, not employees, should provide workplace equipment or compensation for equipment. Don't buy bits for the shop, nails for the foreman, or Cursor for the tech lead.

- the workplace is not a meritocracy. People are not defined by their wealth.

- If $1,000 does not represent an appreciable amount of someone's assets, they are doing well in life. Approximately half of US citizens cannot afford rent if they lose a paycheck.

- Sometimes the money needs to go somewhere else. Got kids? Sick and in the hospital? Loan sharks? A pool full of sharks and they need a lot of food?

- Folks can have different priorities and it's as simple as that

We're (my employer) still unsure if new dev tooling is improving productivity. If we find out it was unhelpful, I'll be very glad I didn't lose my own money.

[swader999]

I agree with all this but the simple fact is that if you don't keep up you'll be out of a job faster than the rest of us. My strategy for being replaced by AI is to replace the company that replaces me. Software is getting trivial to implement, especially if you know how to specify it.

[15123123]

$100 per month for a SaaS is quite a lot outside of Western countries. People are not even spending that much on VPN or Password Manager.

[sagarpatil]

Use free tiers?