581–590 of 603 posts
I see a lot of comments here gushing about CC but I've used and I really don't get it. I find that it takes me just as long to explain to it what I need done as it takes to just do the work myself.
build me a page and the crud endpoints to manage it. -> done in 2 minutes.
Earlier quoted context omitted.
Hmmmm.. I am working in a niche domain (Confidential Computing) and the work is fairly creative, although I wouldn't say I asked it domain-specific things. I didn't ask it to come up with encryption schemes or security protocols, I learned very quickly that it cannot even start on those problems. "Design discussions" were just sycophantic affirmations of whatever I wrote. What I mostly tried were "add this function"…
Oh I've definitely seen that too, even with common front-end stuff. I think people might be exaggerating how much they are out of the loop. Claude often needs to be guided away from stupid decisions, and it will absolutely delete code in order to "fix" a problem. Still, it saves me work on tedious stuff, and makes it more pleasant. I wouldn't ask it to do anything I don't understand, unless I don't care about the res…
I've been using Claude code 12-16 hours a day since I first got it running two weeks ago. Here's the tips I've discovered: 1. Immediately change to sonnet (the cli defaults to opus for max users). I tested coding with opus extensively and it never matches the quality of sonnet. 2. Compacting often ends progress - it's difficult to get back to the same quality of code after compacting. 3. First prompt is very importan…
Earlier quoted context omitted.
This is the core of the issue. You hate coding, and I love it. I chose to be a software engineer not because I like using software, but because I like writing software. If we get to a point where the engineers are replaced by machines, I would hope that the project managers were replaced years before that, as a final act of revenge
This argument is fallacious. I enjoy a lot of things (Software Engineering is one of them) that in NO way determines whether or not AI is coding, nor does it guarantee me a career (just ask all the blacksmiths that disappeared once cars became the mass transport vehicle). The fact that people are going to (possibly) be able to instruct a computer to do whatever they wish without the need of a four year degree and sev…
I see a lot of comments here gushing about CC but I've used and I really don't get it. I find that it takes me just as long to explain to it what I need done as it takes to just do the work myself.
a sentence of english could easily translate to hundreds of lines of code. how is this not obvious. build me a page and the crud endpoints to manage it. -> done in 2 minutes.
Earlier quoted context omitted.
In Germany, software engineer is a trade you go to trade school for three years while working in a company in parallel. I don't think that IT education and computer science in universities should have a stronger focus on SE as universities are basically a trade school for being a researcher.
While that path exists, the vast majority of developers don't go through that path.
* except if you are developing complicated algorithms or do numeric stuff. However, I believe that the majority of developers will never be in such a situation.
Earlier quoted context omitted.
While that path exists, the vast majority of developers don't go through that path.
Yes, but it is more of a cultural thing than anything else. Studying computer science to be a software developer* is like studying mechanical engineering to be a machine operator. * except if you are developing complicated algorithms or do numeric stuff. However, I believe that the majority of developers will never be in such a situation.
So you end up in that weird spot where it would work very well for someone with a strong focus on self-learning and a company investing into their side of the training, but at that point you could almost skip the formal part completely and just start directly, assuming you have some self-taught base. Or work part-time will studying on the side, and get the more useful degree that way. Plenty places will hire promising first-year uni students.
Earlier quoted context omitted.
The fastest way is via struggle. Learn to do it yourself first. Understand WHY it does not work. What's good code? What's bad code? What are conventions? There are no shortcuts - you are not an accountant just because you have a calculator.
With that mindset you don't have to go to school, you could learn everything through struggle... Ideally it's a bit of both, you need theory and experience to succeed.
Earlier quoted context omitted.
5. it's not just docker, give it playwright MCP server so it can see what it is implementing in UI and requests 6. start in plan mode and iterate on the plan until you're happy 7. use slash commands, they are mini prompts you can keep refining over time, including providing starting context and reminding it that it can use tools like gh to interact with Github not sure I agree on 1. 2. compact when you are at a good…
Use agents to validate the code. Is it over engineered, does it conform to conventions and spec, is it actually implemented or half bullshit. I run three of these at the end of a feature or task and it almost always send Opus back to the workbench fixing a bunch of stuff. And since they have their own context, you don't blow up the main context and can go for longer.
Earlier quoted context omitted.
My assembly skills have atrophied terribly, and that's ok.
Using LLMs is not moving up a level of abstraction, it is removing your own brain from the abstraction altogether