Hacker News Reader

Comment by dguest | Hacker News Reader

And here I'm wondering if I'm putting my career at risk by not trying them out.

Probably both are true: you should try them out and then use them where they are useful, not for everything.

HN is full of people who say LLMs aren't good at coding and don't "really" produce productivity gains.

None of my professional life reflects that whatsoever. When used well, LLMs are exceptional and putting out large amounts of code of sufficient quality. My peers have switched entire engineering departments to LLM-first development and are reporting that the whole org is moving 2x as fast even after they fired the 50% of devs who couldn't make the switch and didn't hire replacements.

If you think LLM coding is a fad, your head is in the sand.

The instigators say they were correct and fired the political opponents. Unheard of!

I have no doubt that volumes of code are being generated and LGTM'd.

Right now I'm mostly an "admin" coder: I look at merge requests and tell people how to fix stuff. I point them to LLMs a lot too. People I know who are actually writing a lot of code are usually saying LLMs are nice.

Agreed. I work for a tiny startup where I wear multiple hats, and one of them is DevOps. I manage our cloud infra with Terraform, and anyone who's scaled cloud infrastructure out of the <10 head count company to a successful 500+ company knows how critical it can be to get a wrangle on the infrastructure early. It's basically now or never.

It used to take me days or even multiple sprints to complete large-scale infrastructure projects, largely because of having to repeatedly reference Terraform cloud provider docs for every step along the way.

Now I use Claude Code daily. I use an .md to describe what I want in as much detail as possible and with whatever idiosyncrasies or caveats I know are important from a career of doing this stuff, and then I go make coffee and come back to 99% working code (sometimes there are syntax errors due to provider / API updates).

I love learning, and I love coding. But I am hired to get things done, and to succeed (both personally and in my role, which is directly tied to our organization's security, compliance, and scalability) I can't spend two weeks on my pet projects for self-edification. I also have to worry about the million things that Claude CAN'T do for me yet, so whatever it can take off of my plate is priceless.

I say the same things to my non-tech friends: don't worry about it 'coming for your job' yet - just consider that your output and perceived worth as an employee could benefit greatly from it. If it comes down to two awesome people but one can produce even 2x the amount of work using AI, the choice is obvious.

Yesterday I used Warp’s LLM integrations to write two shell scripts that would have taken me longer to author myself than to do the task manually. Of the three options, this was the fastest by a wide margin.

For this kind of low stakes, easily verifiable task it’s hard to argue against using LLMs for me.

Reply on news.ycombinator.com