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

381–390 of 410 posts

Re: A staff engineer's journey with Claude Code

#381

Post by jaggederest »

fragmede wrote: post #197
jaggederest wrote: post #77

Earlier quoted context omitted.

The key is prompting. Prompt to within an inch of your life. Treat prompts as source code - edit them in files, use @ notation to bring them into the console. Use Claude to generate its own prompts - https://github.com/wshobson/commands/ and https://github.com/wshobson/agents/ are very handy, they include a prompt-engineer persona. I'm at the point now where I have to yell at the AI once in a while, but I touch essen…

How much voice control have you implemented?

None but it's on the list! Actually using it to prototype a complete audio visual tracking and annotation tool, so feeding it back into itself is a logical next step.

Re: A staff engineer's journey with Claude Code

#382

Post by jaggederest »

faangguyindia wrote: post #241
jaggederest wrote: post #101

Earlier quoted context omitted.

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

It does not write anything in plan mode, it's documented here it has only readonly tools available in plan mode: https://docs.anthropic.com/en/docs/claude-code/common-workfl... But here are fine prints, it has "exit plan mode" tool, documented here: https://minusx.ai/blog/decoding-claude-code/#appendix So it can exit plan mode on its own and you wouldn't know!

Ok, it's done it to me 3 times today, so I don't know what to tell you. I remind it that it's in plan mode and it goes "oh no I shouldn't have modified that file then!"

Re: A staff engineer's journey with Claude Code

#383

Post by jaggederest »

EnPissant wrote: post #143
jaggederest wrote: post #101

Earlier quoted context omitted.

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

That's not possible. You are misremembering.

3 times today. I don't know what to say besides it tries to edit files in plan mode often for me

Re: A staff engineer's journey with Claude Code

#384

Post by searene »

bootsmann wrote: post #292
searene wrote: post #191

Earlier quoted context omitted.

Me too. I’ve been playing with various coding agents such as Cursor, Claude Code, and GitHub Copilot for some time, and I would say that their most useful feature is educating me. For example, they can teach me a library I haven’t used before, or help me debug a production issue. Then I would choose to write the code by myself after I’ve figured everything out with their help. Writing code by myself is definitely fas…

> For example, they can teach me a library I haven’t used before. How do you verify it is teaching you the correct thing if you don't have any baseline to compare it to?

You are right, I don't have any baseline. I just try it and see if it works. One good thing about the software field is that I can compile and run the code for verification. It may not be optimal, but at least it's testable.

Re: A staff engineer's journey with Claude Code

#385

Post by mierz00 »

kbuchanan wrote: post #15

For me, working mostly in Planning Mode skips much of the initial misfires, and often leads to correct outcomes for the first edit.

Recently I’ve been taking a step back and getting ChatGPT 5 to ask me questions to create a spec.

I refine that spec and then give that to planning mode and then go from there.

I’ve found if I jump straight into planning mode I miss some critical aspects of what ever it is I am building.

Re: A staff engineer's journey with Claude Code

#386

Post by dchftcs »

rafaelmn wrote: post #294
spicyusername wrote: post #290

I guess we're just going to be in the age of this conversation topic until everyone gets tired of talking about it. Every one of these discussions boils down to the following: - LLMs are not good at writing code on their own unless it's extremely simple or boilerplate - LLMs can be good at helping you debug existing code - LLMs can be good at brainstorming solutions to new problems - The code that is written by LLMs…

> but this was true when they wrote their own code with stack overflow. Searching for solutions and integrating examples found requires effort that develops into a skill. You would rarely get solutions that would just fit into the codebase from SO. If I give a task to you and you produce a correct solution on the initial review I now know I can trust you to deal with this kind of problem in the future. Especially aft…

People obviously turning out LLM code uncritically should be investigated and depending on the findings made redundant. It's a good thing that it allows teams to filter out these people earlier. In my career I have found that a big predictor of the quality of code is the amount of thought put into it and the brains put behind it - procedures like code review can only catch so many things, and a senior's time is saved only when a junior has actually put their brain to work. If someone is shown to never put in thought in their work, they need to make way for people who actually do.

Re: A staff engineer's journey with Claude Code

#387

Post by coverj »

rhubarbtree wrote: post #212

Does 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…

Are there even non-AI development streams/videos that meet this criteria?

Re: A staff engineer's journey with Claude Code

#388

Post by musbemus »

makk wrote: post #187

I don’t understand the use of MCP described in the post. Claude code can access pretty much all those third party services in the shell, using curl or gh and so on. And in at least one case using MCP can cause trouble: the linear MCP server truncates long issues, in my experience, whereas curling the API does not. What am I missing?

You're exactly right. To be honest, in pretty much every case I've seen, indicating usage of a read-only resource directly in the prompt always outperforms using the MCP for it. Should really only be using MCP if you need MCP-specific functionality imo (elicitation, sampling)

Re: A staff engineer's journey with Claude Code

#389

Post by Kiro »

rhubarbtree wrote: post #371
Kiro wrote: post #231

Earlier quoted context omitted.

Very few people want to record themselves doing stuff or have an incentive to convince anyone except for winning internet arguments.

Streaming coding is a popular and widespread activity, and it is usually nothing to do with “convincing” folks.

I was talking about people successfully using LLMs having no reason to convince anyone. Their success is not dependent on converting or even informing other people.

Re: A staff engineer's journey with Claude Code

#390

Post by theshrike79 »

OvbiousError wrote: post #355
rafaelmn wrote: post #294

Earlier quoted context omitted.

> but this was true when they wrote their own code with stack overflow. Searching for solutions and integrating examples found requires effort that develops into a skill. You would rarely get solutions that would just fit into the codebase from SO. If I give a task to you and you produce a correct solution on the initial review I now know I can trust you to deal with this kind of problem in the future. Especially aft…

> So using LLMs as a junior you are just breaking my trust, and we both know you are not a competent reviewer of LLM code - why am I even dealing with you when I'll get LLM outputs faster myself ? This was my experience so far. So much this. I see a 1000 lines super complicated PR that was whipped up in less than a day and I know they didn't read all of it, let alone understand.

This is exactly what code reviews are for, doing reviews with juniors is always time-consuming
Post reply on HN