Revenge of the Junior Developer • Hacker News Board

Re: Revenge of the Junior Developer

#51

Post by ramigb » Sat, Mar 22, 2025, 9:29 PM UTC

rocmcd wrote: post #41

disambiguation wrote: post #12

Everyone: telling me how great AI is. No one: making anything great with AI. Sourcegraph: an AI company, routinely promoting their LLM-optimism blogposts to HN, perpetuating the hype cycle their business model depends on.

This is the true litmus test IMO. If LLMs are so great and make everyone so productive, then where are the results? Where are all of the amazing products being released that otherwise would have required 10x the investment? Shouldn't there be _anything_ we can point to that shows that the "productivity needle" is being moved?

I don't think it makes everyone so productive, tbh! If you really know what you are doing and are willing to burn tokens, it will really take your work to the next level—provided you don’t work with a niche product or language that the models weren’t trained on.

If I may use an analogy, it's like what sampling is for music producers. The sample is out there—it’s already a beautiful sample, full of strings and keys, a glorious 8-bar loop. Anyone can grab it, but not every producer can sell it or turn it into a hit.

In the end, every hype train has some truth to it. I highly suggest you give it a shot, if you haven't already. I’m glad I did—it really helped me a lot, and I am (unfortunately, financially) hooked on it.

Re: Revenge of the Junior Developer

#52

Post by LightHugger » Sat, Mar 22, 2025, 9:30 PM UTC

glitchc wrote: post #23

LightHugger wrote: post #19

Earlier quoted context omitted.

Cryptocurrency allows people who are otherwise limited by draconian payment platform limitations, puritanical moralists who own credit card companies and such to buy and sell things online without being stopped. It's obviously not a good system but it provides a high effort release valve, a fallback mechanism that hopefully will undermine some of these draconian measures. Lots of people have been helped by the existe…

Evidence suggests it's the exact opposite. The only thing crypto has really been good for is a store of value. Sure, it's a volatile commodity, but over any 5 year average window, Bitcoin definitely beats inflation. That makes it a safe store of value.

What evidence? People use it to bypass the payment processor cartels all the time.

Re: Revenge of the Junior Developer

#53

Post by bryanlarsen » Sat, Mar 22, 2025, 9:52 PM UTC

monsieurbanana wrote: post #31

Even if I would agree with everything the article says, I have no idea how the author gets to the conclusion that junior developers will prevail because they are faster at adopting LLMs. Didn't he just made a point about how fast the situation is evolving? I had some FOMO about ai last year, not anymore. I don't care that I don't have time to fully explore the current LLM state of the art, because in a month it will…

It's a counterpoint to Yegge's original post https://sourcegraph.com/blog/the-death-of-the-junior-develop...

And it's not saying his original post is wrong, they should be taken together. He's saying those who adapt to the new paradigm will "win", whether senior or junior.

Re: Revenge of the Junior Developer

#54

Post by bluefirebrand » Sat, Mar 22, 2025, 10:07 PM UTC

hombre_fatal wrote: post #30

danielbln wrote: post #20

Earlier quoted context omitted.

I disagree, agentic coding is amazing for prototyping. It removes a ton of friction and inertia and allows me to try a bunch of ideas to see what works (from a delivery and/or UX perspective). Of course, you should have the systems thinking and experience in place to know what it is you're doing with it at any given point , but for demos and prototypes it has been an absolute boon. Generally, you wouldn't type out th…

A good example of this at the extreme is game design. When you're making a game, it's really expensive to try out different ideas, like a few different implementations of a mechanic. It could be hours of work to make a change. You tend to have to do a lot of thinking to tweak a mechanic in a fundamental way just to see what it feels like, knowing that you're probably going to throw it away. LLMs are really good at th…

> LLMs are really good at this. Make a git branch, ask Claude Code to tweak the physics so that it does X, see what it feels like

How do you verify that Claude did what you wanted?

Maybe more importantly, how do you verify that Claude didn't make a change that you didn't want?

Trying to verify the code changes just by testing the running project seems incredibly careless

Re: Revenge of the Junior Developer

#55

Post by kolektiv » Sat, Mar 22, 2025, 10:23 PM UTC

xyzzy9563 wrote: post #9

I think a lot of people are going to be surprised at how fast "vibe coding" with agents replaces a lot of traditional software engineering. Especially for non-critical software, but eventually where safety matters too since AI can generate tons of test cases.

And without any traditional software engineers, who's going to check that those test cases actually do anything useful and verify the important properties of the system? It doesn't matter how many unit tests your Therac-25 has if none of them test the thing that matters.

Re: Revenge of the Junior Developer

#56

Post by xyzzy9563 » Sat, Mar 22, 2025, 10:49 PM UTC

kolektiv wrote: post #55

xyzzy9563 wrote: post #9

I think a lot of people are going to be surprised at how fast "vibe coding" with agents replaces a lot of traditional software engineering. Especially for non-critical software, but eventually where safety matters too since AI can generate tons of test cases.

And without any traditional software engineers, who's going to check that those test cases actually do anything useful and verify the important properties of the system? It doesn't matter how many unit tests your Therac-25 has if none of them test the thing that matters.

Well theoretically you can also do E2E testing where an AI agent also clicks around a user-interface and takes screenshots, which are then fed back into it.

Re: Revenge of the Junior Developer

#57

Post by fragmede » Sat, Mar 22, 2025, 10:58 PM UTC

hombre_fatal wrote: post #21

LoganDark wrote: post #8

Earlier quoted context omitted.

$300? That much sounds like it would last a year. You don't need to spend anywhere near $300 just to try things out

I burned through $50 credits in a sitting the first time I used Claude Code to see what I could vibe-code from scratch. You're pushing whole files of tokens through it every time you interact with it.

for better or worse, Claude code is less parsimonious with tokens compared to aider for the same thing.

Re: Revenge of the Junior Developer

#58

Post by nickysielicki » Sat, Mar 22, 2025, 11:17 PM UTC

Timber-6539 wrote: post #48

nickysielicki wrote: post #6

I’m usually one of the people complaining about hype cycles, and it’s usually been correct to be pessimistic about them. But in this particular case I have to think a lot of people just haven’t tried it in its best form. No, not a local model on your MacBook. No, not the web interface on the free plan. Go lay down $300 into API credits, spend a weekend (or maybe two) fully setting up aider, really give it a shot. It’…

How much does the Deepseek's equivalent cost?

I know this isn't what you were asking, but the answer is $300. And if I wrote $3000 in the original comment, the answer would be the same. You cannot have enough money.

Re: Revenge of the Junior Developer

#59

Post by fragmede » Sat, Mar 22, 2025, 11:40 PM UTC

bayindirh wrote: post #35

null_name wrote: post #28

Earlier quoted context omitted.

This sapling is twice as large as it was a week ago, which was twice again as large as it was the week before. Why, at this rate, it'll be bigger than the whole world in but a month.

I remembered the dialogue from the movie Snatch: T: What's happening with this sausages, Charlie? C: 2 minutes, Turkish. -- 5 Minutes later --- T: How long for the sausages? C: 5 minutes, Turkish. T: It was 2 minutes, 5 minutes ago. I don't know why I remembered it. Is it AI, or self driving cars, or both. Huh.

self driving cars are here, just unevenly distributed. Waymo operates in several cities already, providing millions of rides to people. Just because you haven't seen them doesn't mean they don't exist.

Re: Revenge of the Junior Developer

#60

Post by fragmede » Sat, Mar 22, 2025, 11:58 PM UTC

jcgrillo wrote: post #45

victorbjorklund wrote: post #43

Earlier quoted context omitted.

You should probably compare the same dev using AI vs not using AI. Otherwise you can use that argument for anything. Notepad is a better IDE than emacs if we compare a really good dev using notepad vs a shitty dev using emacs.

Ok, if I notice other devs suddenly getting 5x as productive I'll give it a try, but so far no such effect has been demonstrated. It seems like a pretty straightforward research question, and you'd think if there was any demonstrable effect the companies selling these things would use such research to market their products. So where is it?

There's a dead body lying there but you won't believe they're actually dead until someone creates a video reenactment of the killer stabbing them and shoves that video in your face?

Speaking of videos, https://youtu.be/opi1s_5Dm-c is probably below your level and it's kinda long.