31–40 of 675 posts
Takes on dev-focused AI is so divided right now. Appears some people just don’t understand the workflows that are effective. It actually takes a lot of work to set it up. It’s not as simple as typing in prompts.
> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…
Easily 99% of comments generated by LLMs are useless.
# loop over the images
for filename in images_filenames:
# download the image
image = download_image(filename)
# resize the image
resize_image(image)
# upload the image
upload_image(image)> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…
Easily 99% of comments generated by LLMs are useless.
I prefer to push for self documenting code anyway, never saw the need for docs other than for an API when I'm calling something like a black box.
Maybe LLMs make you 10x faster at using boilerplate-heavy things like Shadcn/ui or Tanstack.
...which is still only about half as fast as using a sane ecosystem.
IMO this is why there's so many diverging opinions about the productivity of AI tools.
> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…
Easily 99% of comments generated by LLMs are useless.
> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…
Do you have a link to some of the code that you have produced using this approach? I am yet to see a public or private repo with non-trivial generated code that is not fundamentally flawed.
> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…
I think its only a matter of time until our roles are commoditized and vibe-coding becomes the norm in most industries.
Vibe coding being a dismissive term on developing a new skillset. For example we'll be doing more planning and testing and such instead of writing code. The same way, say, sysadmins just spin up k8s instead of racking servers or car mechanics read diagnosis codes from readers and, often, just replace an electric part instead of hand-tuning carbs or gapping spark plugs and such. That is to say, a level of skill is being abstracted away.
I think we just have to see this, most likely, as how things will get done going forward.
Earlier quoted context omitted.
Do you have a link to some of the code that you have produced using this approach? I am yet to see a public or private repo with non-trivial generated code that is not fundamentally flawed.
That's disingenuous or naive. Almost nobody decides to expressly highlight the section of code (or whole files generated by ai) they just get on with the job when there's real deadlines and it's not about coding for the sake of the art form...
In other words, it matters whether the AI is creating technical debt.
I dont use ai code generation tools, I just use claude as a search engine. It hasn't changed the output rate of my code but I believe that its improved the quality of it by exposing me to patterns and features that I otherwise may not have. I used to take a very object oriented approach to code, but when I would ask claude to look at my code and critique it, it would often lead me into more functional patterns, with…
Then unfortunately you're leaving yourself at a serious disadvantage.
Good for you if you're able to live without a calculator, but frankly the automated tool is faster and leaves you less exhausted so you should be taking advantage of it.