Hacker News Reader

Comment by aprdm | Hacker News Reader

lol same. I just wrote a bunch of diagrams with mermaid that would legit take me a week, also did a mock of an UI for a frontend engineer that would take me another week to do .. or some designers. All of that in between meetings...

Waiting for it to actually go well to see what else I can do !

View on HN

The more I have this experience and read people maligning AI for coding, the more I think the junior developers are actually not the ones in danger.

Oh I've thought this for years. As an L7, basically my primary role is to serve as someone to bounce ideas off of, and to make recommendations based on experience. A chatbot, with its virtually infinite supply of experience, could ostensibly replace my role way sooner than it could a solid junior/mid-level coder. The main thing it needs is a consistent vision and direction that aligns with the needs of nearby teams, which frankly sounds not all that hard to write in code (I've been considering doing this).

Probably the biggest gap would be the ability to ignite, drive, and launch new initiatives. How does an AI agent "lead" an engineering team? That's not something you can code up in an agent runtime. It'd require a whole culture change that I have a hard time seeing in reality. But of course if there comes a point where AI takes all the junior and mid-level coding jobs, then at that point there's no culture to change, so staff/principal jobs would be just as at risk.

I dont think it's a replacement for that but it's definitely provides some of it. Whereas senior+ level people were required before.

I think that's sort of a theme with LLMs. It's not that it's better than "the real thing" (in this case a senior+ software engineer) or that its without flaws... but it's a fucking service. Having just a semblance of an advanced software engineer in your pocket is a game changer. It doesn't need to be perfect or better than the real thing to fundamentally change things.

I have the complete opposite impression w.r.t. architecture decisions. The LLMs can cargo cult an existing design, but they do not think through design consequences well at all. I use them as a rubber duck non-stop, but I think I respect less than one out of every six of their suggestions.

They've gotten pretty good IME so long as you guide it to think out of the box, give it the right level of background info, have it provide alternatives instead of recommendations, and do your best not to bias it in any particular direction.

That said, the thing it really struggles with is when the best approach is "do nothing". Which, given that a huge chunk of principal level work is in deciding what NOT to do, it may be a while before LLMs can viably take that role. A principal LLM based on current tech would approve every idea that comes across it, and moreover sell each of them as "the exact best thing needed by the organization right now!"

Knowing when to nudge it out of a rut (or say skip it) is probably the biggest current skill. This is why experienced people get generally much better results.

I’m not sure. I keep asking the LLMs whether I should rewrite project X in language Y and it just asks back, “what’s your problem?” And most of the times it shoots my problems down showing exactly why rewriting won’t fix that particular problem. Heck, it even quoted Joel Spolsky once!

Of course, I could just _tell_ it to rewrite, but that’s different.

Damn, I'm sure even I'd have caved at some point. Did you get to VHDL? Your project etched in pure silicon? Yes! Must!

Oh no, my job is safe no longer!

I have been able to prototype way faster. I can explain how I want a prototype reworked and it's often successful. Doesn't always work, but super useful more often than not.

That line on the chart labeled “profit” is really going to go up now!

Reply on news.ycombinator.com