131–140 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.
Earlier quoted context omitted.
> The code I generate is usually better than what I'd do by hand. I'm always baffled by this. If you can't do it that well by hand, how can you discriminate its quality so confidently? I get there is a artist/art consumer analogy to be made (i.e. you can see a piece is good without knowing how to paint), but I'm not convinced it is transferrable to code. Also, not really my experience when dealing with IaC or (comple…
You're forgetting that code quality also requires time. Developers make tradeoffs all the time on how much time to invest into improving the quality of what they write, for both new and existing code. When someone claims that LLMs can produce higher-quality code it can include quality levels that may be unjustifiably slow to hand-craft depending on constraints and needs. Related - agentic LLMs may be slow to produce…
The full year is just the more of the above.
It makes everyone “produce more code” but your worst dev producing 10X the code is not 10X more productive.
There’s also a bit of a dunning Kruger effect where the most careless people are the most likely to YOLO thousands of lines of vibecode into prod. While a more meticulous engineer might take a lot more time to read the changes, figure out where the AI is wrong, and remove unnecessary code. But the second engineer would be seen as much much less productive than the first in this case
Earlier quoted context omitted.
Let’s talk about rules and docs, shall we? What makes a good rule for AI to keep it on task? What are your setups for docs and attaching them to the context (do you need to? Or just the location?) Let’s boil this down to an easy set of reproducible steps any engineer can take to wrangle some sense from their AI trip.
Aka, let's train people how to use the tool...
> 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…
> The code I generate is usually better than what I'd do by hand. I'm always baffled by this. If you can't do it that well by hand, how can you discriminate its quality so confidently? I get there is a artist/art consumer analogy to be made (i.e. you can see a piece is good without knowing how to paint), but I'm not convinced it is transferrable to code. Also, not really my experience when dealing with IaC or (comple…
With AI the extra quality and polish is basically free and instantaneous.
Now for senior developers, AI has been tremendous. Example: I'm building a project where I hit the backend in liveview, and internally I have to make N requests to different APIs in parallel and present the results back. My initial version to test the idea had no loading state, waiting for all requests to finish before sending back.
I knew that I could use Phoenix Channels, and Elixir Tasks, and websockets to push the results as they came in. But I didn't want to write all that code. I could already taste it and explain it. Why couldn't I just snap my fingers?
Well AI did just that. I wrote what I wanted in depth, and bada bing, the solution I would have written is there.
Vibe coders are not gonna make it.
Engineers are having the time of their lives. It's freeing!
Earlier quoted context omitted.
I think the comment was showing that the project takes 9 weeks either way, but coming to that determination was much more confident and convincing with a functional demo versus a hand-wavy figma + guesstimate.
> was much more confident and convincing with a functional demo versus a hand-wavy figma + guesstimate. Except it also blurs the lines and sets incorrect expectations. Management often see code being developed quickly (without full understanding of the fine line between PoC and production ready) and soon they expect it to be done with CC in 1/2 the time or less. Figma on the other hand makes it very clear it is not c…
I thought this would be another AI hate article, but it made some great points. One thing that AI has helped me with is finding pesky bugs. I mainly work on numerical simulations. At one point I was stuck for almost a week trying to figure out why my simulation was acting so strange. Finally I pulled up chatgpt, put some of my files into the context and wrote a prompt explaining the strange behavior and what I though…
It’s a rubber duck that’s pretty educated and talks back.