181–190 of 387 posts
Earlier quoted context omitted.
I've had a lot of enjoyment flipping the agentic workflow around: code manually and ask the agent for code review. Keeps my coding skills and knowledge of the codebase sharp, and catches bugs before I commit them!
if it catches a lot of bugs maybe you’d be better of letting it write it in the first place :)
I wish more was being invested in AI autocomplete workflows. That was a nice middle-ground. But yeah my hunch is "the old way" - although not sure we can even call it that - is likely still on par with an "agentic" workflow if you view it through a wider lens. You retain much better knowledge of the codebase. You improve your understanding over coding concepts (active recall is far stronger than passive recognition).
AI autocomplete sucked. Everyone quickly moved on because it is not a useful interface
I wish more was being invested in AI autocomplete workflows. That was a nice middle-ground. But yeah my hunch is "the old way" - although not sure we can even call it that - is likely still on par with an "agentic" workflow if you view it through a wider lens. You retain much better knowledge of the codebase. You improve your understanding over coding concepts (active recall is far stronger than passive recognition).
AI autocomplete sucked. Everyone quickly moved on because it is not a useful interface
> Everyone moved on
> it is not a useful interface
You've made three claims in your brief comment and all appear to be false. Elaborate what you mean by any of this?
I did things the old way for 25 years and my carpal tunnels are wearing out. LLMs let me produce the same quality I always have with a lot less typing so not mad at that at all. I review and own every line I commit, and feel no desire to go back to the old way. What scares the shit out of me are all these new CS grads that admit they have never coded anything more complex than basic class assignments by hand, and jus…
From what I remember, typical new C++ debugged code speed is about 20-25K lines per year, lines that are non-blank, non-comment and not completely verifiable by compiler. E.g., standalone bracket or comma or semicolon are not lines of code, function header is too not a line of code, but computation, conditions and loops are. This is from old IBM statistics, I learned about it circa 2007. If we assume that there are 5…
In what way? You're either very young or very old, right? Voice-to-text has been a common way to input text online since iPhone. Someone commented on HN != they typed that many words with their fingers.
I wish more was being invested in AI autocomplete workflows. That was a nice middle-ground. But yeah my hunch is "the old way" - although not sure we can even call it that - is likely still on par with an "agentic" workflow if you view it through a wider lens. You retain much better knowledge of the codebase. You improve your understanding over coding concepts (active recall is far stronger than passive recognition).
I've had a lot of enjoyment flipping the agentic workflow around: code manually and ask the agent for code review. Keeps my coding skills and knowledge of the codebase sharp, and catches bugs before I commit them!
I'm a big advocate for AI, including GenAI. But I still spend a fair amount of time coding by hand, or "by hand + Copilot completions enabled". And yes, I will use spec driven development with SpecKit + OpenCode, or just straight up "vibe code" on occasion but so far I am unwilling to abdicate my responsibility to understand code and abandon the knowledge of how to write it. Heck, I even bought a couple of new LISP a…
My responsibility is to make sure my code meets functional and non functional requirements. It’s to understand the *behavior*. My automated unit, integration, and load tests confirm that. Someone thought I was naive when I said my vibe coded internal web admin site met the security requirements without looking at a line of code. I knew that because the requirements were that anyone who had access to the site could do…
Do they? Did you write them? If not, how do you know they confirm the desired behavior? If your tests are AI generated (and not human reviewed) then even if you're doing spec-driven development and provide a comprehensive spec, how can you be sure the tests actually test the desired behavior?
Now if you're either writing or reviewing the tests, then sure.
Also, for what it's worth, when I talk about my "responsibility" I'm speaking more from a self-imposed sense of... um, almost a moral responsibility I feel, not something involving a 3rd party like a customer or employer.
I am this very term teaching 18-year-old students 6502 assembly programming using an emulated Apple II Plus. They've had intro to Python, data structures, and OO programming courses using a modern programming environment. Now, they are programming a chip from the seventies using an editor/assembler that was written in 1983 and has a line editor, not a full-screen one. We had a total of 10 hours of class + lab where I…
I wish more was being invested in AI autocomplete workflows. That was a nice middle-ground. But yeah my hunch is "the old way" - although not sure we can even call it that - is likely still on par with an "agentic" workflow if you view it through a wider lens. You retain much better knowledge of the codebase. You improve your understanding over coding concepts (active recall is far stronger than passive recognition).
I hope if/when diffusion models get a little more traction down the line it'll put some new life into autocomplete(-adjacent) workflows. The virtually instantaneous responses of Inception's Mercury models [0] still feel a little like magic; all it's missing is the refinement and deep editor integration of Cursor.
On the subject of diffusion models, it's a shame there aren't any significant open-weight models out there, because it seems like such a perfect fit for local use.
Here’s how i do it: I create a lot of stuff using AI to the max, but I also spend the necessary of time on reviewing that the AI is producing code that passes my cognitive load standards. this involves some tokens spent on grooming code and documenting well. Most of this is effortless thanks to an AGENTS.md based on this: https://github.com/zakirullin/cognitive-load/blob/main/READM... but i have a good sense of catch…
I can't do it. If I let an LLM write code for me, that code is untouchable. I see it as a black box, that I will categorically refuse to open. If it works, I use it, but don't trust it. If it breaks, I get frustrated. The only way that works for me is me behind the driving wheel at all times and an LLM as an assistant that answers my questions. We either brainstorm something or it helps me express things I know in languages syntax. Somehow that step has always been a bit of a burden for me - I understood the concepts well, but expressing them in syntax was a bit of a difficulty.
Earlier quoted context omitted.
I've had a lot of enjoyment flipping the agentic workflow around: code manually and ask the agent for code review. Keeps my coding skills and knowledge of the codebase sharp, and catches bugs before I commit them!
if it catches a lot of bugs maybe you’d be better of letting it write it in the first place :)