Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A staff engineer's journey with Claude Code

sanity.io

Post reply on HN
Print view View original

101–110 of 410 posts

Re: A staff engineer's journey with Claude Code

#101

Post by jaggederest »

adastra22 wrote: post #95
jaggederest wrote: post #70

Earlier quoted context omitted.

> That will prevent it from eagerly implementing stuff. In theory. In practice, it's not a very secure sandbox and Claude will happily go around updating files if you insist / the prompt is bad / it goes off on a tangent. I really should just set up a completely sandboxed VM for it so that I don't care if it goes rm-rf happy.

Plan mode disabled the tools, so I don’t see how it would do that. A sandboxed devcontainer is worth setting up though. Lets me run it with —dangerously-skip-permissions

I don't know either but I've seen it write to files in plan mode. Very confusing.

Re: A staff engineer's journey with Claude Code

#103

Post by adastra22 »

lordnacho wrote: post #46
abraxas wrote: post #44

Earlier quoted context omitted.

I tried to follow the same pattern on a backend project written in Python/FastAPI and this has been mostly a heartache. It gets kind of close but then it seems to periodically go off the rails, lose its mind and write utter shit. Like braindead code that has no chance of working. I don't know if this is a question of the language or what but I just have no good luck with its consistency. And I did invest time into de…

Has this got anything to do with using a stronger typed language? I've heard that reported, not sure whether it's true since my python scripts tend to be short. Does it end in a forever loop for you? I used to have this problem with other models.

I also use Rust with Claude Code, like GP. I do not experience forever loops — Claude converges on a working compiling solution every time. Sometimes the solution is garbage, and many times it gets it to “work” by disabling the test. I have layers of scaffolding (critic agents) that prevent this from being something I have to deal with, most of the time.

But yeah, strongly typed languages, test driven development, and good high quality compiler errors are real game changers for LLM performance. I use Rust for everything now.

Re: A staff engineer's journey with Claude Code

#104

Post by sdesol »

albingroen wrote: post #32

So we’re supposed to start paying $1k-$1,5k on top of already crazy salaries just to maybe get a productivity boost on trivial to semi trivial issues? I know my boss would not be keen on that at least.

It will certainly be interesting to see how businesses evolve in the upcoming years. What is written in stone is, you (employee) will be measured and I am curious to see what developers will be measured by in the future. Will you be at a greater risk of layoffs/lack of promotions/etc. if you spend more on AI? How do you as a developer prove that it is you and not the LLM that should be praised?

Re: A staff engineer's journey with Claude Code

#105

Post by adastra22 »

sfjailbird wrote: post #17
shinecantbeseen wrote: post #11

Earlier quoted context omitted.

I’m with you. Sometimes it really just feels like we’re just tacking on the cognitive load of managing the drunk senior in addition to the problem of hand instead of just dealing with the problem at hand.

A hundred times more time is spent reading a given piece of code, than it took writing it, in the lifetime of that program. OK I made up the statistic, but the core idea is true, and it's something that is rarely considered in this debate. At least with code you wrote, you can probably recognize it later when you need to maintain it or just figure out what it does.

Most code is never read, to be honest.

Re: A staff engineer's journey with Claude Code

#106

Post by criemen »

noosphr wrote: post #9
jason_zig wrote: post #4

Earlier quoted context omitted.

I've seen people post this same advice and I agree with you that it works but you would think they would absorb this common strategy and integrate it as part of the underlying product at this point...

The people who build the models don't understand how to use the models. It's like asking people who design CPUs to build data-centers. I've interviewed with three tier one AI labs and _no-one_ I talked to had any idea where the business value of their models came in. Meanwhile Chinese labs are releasing open source models that do what you need. At this point I've build local agentic tools that are better than anythin…

> The people who build the models don't understand how to use the models. It's like asking people who design CPUs to build data-centers.

This doesn't match the sentiment on hackernews and elsewhere that claude code is the superior agentic coding tool, as it's developed by one of the AI labs, instead of a developer tool company.

Re: A staff engineer's journey with Claude Code

#107

Post by meerab »

f311a wrote: post #82
meerab wrote: post #62

I have barely written any code since my switch to Claude Code! It's the best thing since sliced bread! Here's what works for me: - Detailed claude.md containing overall information about the project. - Anytime Claude chooses a different route that's not my preferred route - ask my preference to be saved in global memory. - Detailed planning documentation for each feature - Describe high-level functionality. - As I de…

What you’re working on? In my industry it fails half of the time and comes up with absolute nonsense. The data just don’t exist for our problems, it can only work when you guide it and ask for a few functions at max.

I am working on VideoToBe.com - and my stack is NextJS, Postgresql and FastAPI.

Claude code is amazing at producing code for this stack. It does excellent job at outputting ffmpeg, curl commands, linux shell script etc.

I have written detailed project plan and feature plan in MarkDown - and Claude has no trouble understanding the instructions.

I am curious - what is your usecase?

Re: A staff engineer's journey with Claude Code

#108

Post by bongodongobob »

rester324 wrote: post #35

> If I were to give advice from an engineer's perspective, if you're a technical leader considering AI adoption: >> Let your engineers adopt and test different AI solutions: AI-assisted coding is a skill that you have to practice to learn. I am sorry, but this is so out of touch with reality. Maybe in the US most companies are willing to allocate you 1000 or 1500 USD/month/engineer, but I am sure that in many countri…

Depends on the culture. I worked at a place that did $100 million in sales a year and if the cost was less than $5k for something we needed, management said just fuckin do it, don't even ask. I also worked at a place that did $2 billion a year and they required multi-level approval for MS project pro licenses. All depends.

Edit: Why is this downvoted? Different corp cultures have different ideas about what is worthwhile. Some places value innovation and experimentation and some places don't.

Re: A staff engineer's journey with Claude Code

#109

Post by mumbisChungo »

utyop22 wrote: post #83
dontlaugh wrote: post #51

Earlier quoted context omitted.

At that point, why not just write the code yourself?

I'm finding what's happening right now kinda bizarre. The funny thing is - we need less. Less of everything. But an up-tick in quality. This seems to happen with humans with everything - the gates get opened, enabling a flood of producers to come in. But this causes a mountain of slop to form, and overtime the tastes of folks get eroded away. Engineers don't need to write more lines of code / faster - they need to ge…

>ones thinking power is diminished overtime by interacing with LLMs etc.

Sometimes I reflect on how much more efficiently I can learn (and thus create) new things because of these technologies, then get anxiety when I project that to everyone else being similarly more capable.

Then I read comments like this and remember that most people don't even want to try.

Re: A staff engineer's journey with Claude Code

#110

Post by meerab »

jazzyjackson wrote: post #96
meerab wrote: post #62

I have barely written any code since my switch to Claude Code! It's the best thing since sliced bread! Here's what works for me: - Detailed claude.md containing overall information about the project. - Anytime Claude chooses a different route that's not my preferred route - ask my preference to be saved in global memory. - Detailed planning documentation for each feature - Describe high-level functionality. - As I de…

Does Claude Code provide some kind of "global memory" the llm refers to, or is this just a request you make within the the llm's context window? Just curious hadn't heard the use of the term EDIT: I see, you're asking Claude to modify claude.md to track your preference there, right? https://docs.anthropic.com/en/docs/claude-code/memory

Yes. /init will initialize the project and save initial project information and preference.

Ask Claude to update the preference and document the moment you realize that claude has deviated away from the path.

Post reply on HN