[dead]
A staff engineer's journey with Claude Code
211–220 of 410 posts
Re: A staff engineer's journey with Claude Code
#212Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype.
I want the code to have subsequently been deployed in production and demonstrably robust, without additional work outside of the livestream.
The livestream should include code review, test creation, testing, PR creation.
It should not be on a greenfield project, because nearly all coding is not.
I want to use Claude and I want to be more productive, but my experience to date is that for writing code beyond autocomplete AI is not good enough and leads to low quality code that can’t be maintained, or else requires so much hand holding that it is actually less efficient than a good programmer.
There are lots of incentives for marketing at the grassroots level. I am totally open to changing my mind but I need evidence.
Re: A staff engineer's journey with Claude Code
#213Earlier quoted context omitted.
At that point, why not just write the code yourself?
I reached this conclusion pretty quickly. With all the hand holding I can write it faster - and it’s not bragging, almost anyone experienced here could do the same. Writing the code is the fast and easy part once you know what you want to do. I use AI as a rubber duck to shorten that cycle, then write it myself.
Writing the code in the grand scheme of things isn't the hard part in software development. The hard parts are architecture and actually building the right thing, something an LLM can't really help you with.
It's not AI, there is no intelligence. A language model as the name says deals with language. Current ones are surprisingly good at it but it's still not more than that.
Re: A staff engineer's journey with Claude Code
#214Avoiding the boilerplate is part of the job as a software developer. Abstracting the boilerplate is how you make things easier for future you. Giving it to an AI to generate just makes the boilerplate more of a problem when there's a change that needs to be made to _all_ the instances of it. Even worse if the boilerplate isn't consistent between copies in the codebase.
Yeah. I'm increasingly starting to think this LLM stuff is simply the first time many programmers have been able to not write boilerplate. They didn't learn to build abstractions so essentially live on whatever platform someone else has built for them. AI is simply that new platform.
I'm lazy af. I have not been manually typing up boilerplate for the past 15 years. I use computers to do repetitive tasks. LLMs are good at some of them, but it's just another tool in the box for me. For some it seems like their first and only one.
What I can't understand is how people are ok with all that typing that you still have to do just going into /dev/null while only some translation of what you wrote ends up in the codebase. That one makes me even less likely to want to type. At least if I'm writing source code I know it's going into the repository directly.
Re: A staff engineer's journey with Claude Code
#215It’s about time these types of articles actually include the types of tasks being “orchestrated” (as the author writes) that aren’t just plain refactoring chores or React boilerplate. Sanity has quite a backlog of long-requested features and the message here is that these agents are supposedly parallelizing a lot of the work. What kind of staff engineer has “80% of their code” written by a “junior developer who doesn…
IMO “junior developer who doesn't learn“ is not quite right. Claude is more like an senior, highly academic engineer who has read all the literature but hasn't ever written any code. Amazing encyclopaedic knowledge, zero taste. I've been building commercial codebases with Claude for the last few months and almost all of my input is on taste and what defines success. The code itself is basically disposable.
> The code itself is basically disposable.
This is key. We’re in mass production of software era. It’s easier and cheaper to replace a broken thing/part than to fix it, things being some units of code.
Re: A staff engineer's journey with Claude Code
#216It’s about time these types of articles actually include the types of tasks being “orchestrated” (as the author writes) that aren’t just plain refactoring chores or React boilerplate. Sanity has quite a backlog of long-requested features and the message here is that these agents are supposedly parallelizing a lot of the work. What kind of staff engineer has “80% of their code” written by a “junior developer who doesn…
We have all these superpowered AI vibe coders, and yet open source projects still have vast backlogs of open issues. Things that make you go "Hmmmmmm."
You have to pay a recurring subscription to access the worthwhile tools in a meaningful capacity. This goes directly against why retail users of open source software, some of whom are also developers of it, actually use it - and you can tell a lot of developers do it because they find coding fun.
It’s a very different discussion when you’re building a product to sell.
Re: A staff engineer's journey with Claude Code
#217Maybe I’m contrarian but I design and write most of my code and let LLMs do the reviews. Why?
First I know my problem space better than the LLM.
Second, the best way to express coding intention is with code. The models often have excellent suggestions on improvements I wouldn’t have thought of. I suspect the probability of providing a good answer has been increased significantly by narrowing the scope.
Another technique is to say “do this like does it” but I suspect that might be close to copyright theft.
Re: A staff engineer's journey with Claude Code
#218Earlier quoted context omitted.
Hardware companies routinely license individual EDA tool seats that cost more than numerous developer salaries - $1k/year is nothing if it improves productivity by any measurable amount.
The OP was saying it's $1k/mo. That's a 5-10% raise, which is a bit more than nothing.
It isn’t a raise. Salaries are on a very different budget. Money is fungible etc but don’t tell accounting.
Re: A staff engineer's journey with Claude Code
#219> budget for $1000-1500/month for a senior engineer going all-in on AI development. Is this another case of someone using API keys and not knowing about the claude MAX plans? It's $100 or $200 a month, if you're not pure yolo brute-force vibe coding $100 plan works. https://www.anthropic.com/max
The MAX plan is a consumer plan, it’s not available with Teams or Enterprise. They introduced a premium team plan ($150) with Claude code access but not sure how much usage that bundles.
Re: A staff engineer's journey with Claude Code
#220Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…
[flagged]