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

201–210 of 410 posts

Re: A staff engineer's journey with Claude Code

#201

Post by 2muchcoffeeman »

shortstuffsushi wrote: post #157
2muchcoffeeman wrote: post #63

Earlier quoted context omitted.

I’ve been trapped in a hole of “can I get the agent to do this?” And the change would have taken me 1/10th the time. Choosing the battles to pick is part of the skill at the moment. I use AI for a lot of boiler plate, tedious tasks I can’t quite do a vim recording for, small targeted scripts.

A similar, non-LLM battle, is a global find and replace, but _not quite identical_ everywhere. Do I just go through the 20 files and do it myself, or try to get clever with regex? Which is ultimately faster...

In this case LLM is probably the answer. I’ve done this exact thing. No messing with regex or manual work. Type a sentence and examine the result in a diff.

Re: A staff engineer's journey with Claude Code

#202

Post by laborcontract »

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.

No, it is possible. I just got it to write files both using Bash and its Write tools while in plan mode right now.

Re: A staff engineer's journey with Claude Code

#203

Post by baq »

shortstuffsushi wrote: post #157
2muchcoffeeman wrote: post #63

Earlier quoted context omitted.

I’ve been trapped in a hole of “can I get the agent to do this?” And the change would have taken me 1/10th the time. Choosing the battles to pick is part of the skill at the moment. I use AI for a lot of boiler plate, tedious tasks I can’t quite do a vim recording for, small targeted scripts.

A similar, non-LLM battle, is a global find and replace, but _not quite identical_ everywhere. Do I just go through the 20 files and do it myself, or try to get clever with regex? Which is ultimately faster...

I’ve just had to do just this, a one line prompt and one example was the difference between mind numbing work and a comfortable cup of coffee away from the monitor.

Re: A staff engineer's journey with Claude Code

#204

Post by muzani »

asdev wrote: post #67

Guy said a whole lot of nothing. Said he's improved productivity, but also said AI falls short in all the common ways people have noticed. Also guarantee no one is building core functionality delegating to Claude Code.

This whole article is a really odd take. Maybe it's upvoted so much because it's from a "staff engineer". Most people are getting much better rates than 95% failure and almost nobody is spending over $1000 a month. If it was anyone else saying the same thing, they'd be laughed out of the room.

Re: A staff engineer's journey with Claude Code

#206

Post by baq »

whateveracct wrote: post #181
swframe2 wrote: post #3

Preventing garbage just requires that you take into account the cognitive limits of the agent. For example ... 1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next. 2) For really complex steps, ask the model to write code to visualize the problem and solution. 3) If the model fails on a given step, ask it t…

that sounds like just coding it yourself with extra steps

Exactly, then you launch ten copies of yourself and write code to manage that yourself, maybe.

Re: A staff engineer's journey with Claude Code

#207

Post by renegat0x0 »

swframe2 wrote: post #3

Preventing garbage just requires that you take into account the cognitive limits of the agent. For example ... 1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next. 2) For really complex steps, ask the model to write code to visualize the problem and solution. 3) If the model fails on a given step, ask it t…

Huh, I thought that AI was made to be magic. Click and it generates code. Turns out it is like magic, but you are an apprentice, and still have to learn how to wield it.

Re: A staff engineer's journey with Claude Code

#208

Post by globular-toast »

mindwok wrote: post #171
ale wrote: post #45

It’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.

If the code is disposable then where do all the rules and reasoning etc live apart from in your head?

Re: A staff engineer's journey with Claude Code

#209

Post by NitpickLawyer »

thayne wrote: post #161
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…

This works fairly well for well defined, repetitive tasks. But at least for me, if you have to put that much effort into the prompt, it is likely easier just to write the code myself.

I've found it works really well for exploration as well. I'll give it a new library, and ask it to explore the library with "x goal" in mind. It then goes and agents away for a few minutes, and I get a mini-poc that more often than not does what I wanted and can also give me options.

Re: A staff engineer's journey with Claude Code

#210

Post by NitpickLawyer »

com2kid wrote: post #159
swframe2 wrote: post #3

Preventing garbage just requires that you take into account the cognitive limits of the agent. For example ... 1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next. 2) For really complex steps, ask the model to write code to visualize the problem and solution. 3) If the model fails on a given step, ask it t…

> 1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next. I asked Claude Code to read a variable from a .env file. It proceeded to write a .env parser from scratch. I then asked it to just use Node's built in .env file parsing.... This was the 2nd time in the same session that it wrote a .env file parser from…

Check your settings, they might be unable to read .env files as a guardrail.
Post reply on HN