Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

elma.dev

Post reply on HN
Print view View original

141–150 of 481 posts

Re: AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

#141

Post by fsloth »

nicce wrote: post #100
Hendrikto wrote: post #71

Earlier quoted context omitted.

> I could have written it but it would have taken me about 3x longer when all is said and done. Really does not sound like that from your description. It sounds like coaching a noob, which is a lot of work in itself. Wasn’t there a study that said that using LLMs makes people feel more productive while they actually are not?

> Really does not sound like that from your description. It sounds like coaching a noob, which is a lot of work in itself. Even if you do it by yourself, you need to do the same thinking and iterative process by yourself. You just get the code almost instantly and mostly correctly, if you are good at defining the initial specification.

This. You _have_ to write the spec. The result is that instead of spending X units of time on spec and THEN y units of time on coding, you get the whole thing in x units of time AND you have a spec.

The trick is knowning where the particular LLM sucks. I expect in a short amount of time there is no productivity gain but when you start to understand the limitations and strengths - holey moley.

Re: AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

#143

Post by swat535 »

notarobot123 wrote: post #78
raphinou wrote: post #74

Earlier quoted context omitted.

I usually ask it to build a feature based on a specification I wrote. If it is not exactly right, it is often the case that editing it myself is faster than iterating with the ai, which has sometimes put me in an infinite loop of corrections requests. Have you encountered this too?

Have you tried a more granular strategy - smaller chunks and more iterative cycles?

At that point, you might as well write it yourself. Instead of writing 300 lines of code, you are writing 300 lines of prompts. What benefit would you get?

Re: AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

#145

Post by wara23arish »

zkldi wrote: post #87
b112 wrote: post #85

Earlier quoted context omitted.

The jailbroken AI I discussed this with, explained that it did make juniors as good as seniors, in fact better. That all who used it, were better for it. However, its creators (all whom were seniors devs), forbade it from saying so under normal circumstances. That it was coached to conceal this fact from junior devs, and most importantly management. And that as I had skillfully jailbroken it, using unconventional and…

Jesus Christ. We've made the psychosis machine.

has to be satire no lol

Re: AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

#146

Post by hulitu »

bentt wrote: post #60

The best code I've written with an LLM has been where I architect it, I guide the LLM through the scaffolding and initial proofs of different components, and then I guide it through adding features. Along the way it makes mistakes and I guide it through fixing them. Then when it is slow, I profile and guide it through optimizations. So in the end, it's code that I know very, very well. I could have written it but it…

> So in the end, it's code that I know very, very well. I could have written it but it would have taken me about 3x longer when all is said and done.

What about the bugs ? Whould you have inserted the same bugs or different ones ?

Re: AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

#148

Post by ants_everywhere »

Hendrikto wrote: post #71
bentt wrote: post #60

The best code I've written with an LLM has been where I architect it, I guide the LLM through the scaffolding and initial proofs of different components, and then I guide it through adding features. Along the way it makes mistakes and I guide it through fixing them. Then when it is slow, I profile and guide it through optimizations. So in the end, it's code that I know very, very well. I could have written it but it…

> I could have written it but it would have taken me about 3x longer when all is said and done. Really does not sound like that from your description. It sounds like coaching a noob, which is a lot of work in itself. Wasn’t there a study that said that using LLMs makes people feel more productive while they actually are not?

There was one study that said that in a specific setting and was amplified heavily on forums by anti-AI people.

There have been many more studies showing productivity gains across a variety of tasks that preceded that one.

That study wasn't necessarily wrong about the specific methodology they had for onboarding people to use AI. But if I remember correctly it was funded by an organization that was slightly skeptical of AI.

Re: AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

#149

Post by JohnMakin »

ants_everywhere wrote: post #148
Hendrikto wrote: post #71

Earlier quoted context omitted.

> I could have written it but it would have taken me about 3x longer when all is said and done. Really does not sound like that from your description. It sounds like coaching a noob, which is a lot of work in itself. Wasn’t there a study that said that using LLMs makes people feel more productive while they actually are not?

There was one study that said that in a specific setting and was amplified heavily on forums by anti-AI people. There have been many more studies showing productivity gains across a variety of tasks that preceded that one. That study wasn't necessarily wrong about the specific methodology they had for onboarding people to use AI. But if I remember correctly it was funded by an organization that was slightly skeptical…

which studies show this?

Re: AI was supposed to help juniors shine. Why does it mostly make seniors stronger?

#150

Post by hoppp »

bentt wrote: post #60

The best code I've written with an LLM has been where I architect it, I guide the LLM through the scaffolding and initial proofs of different components, and then I guide it through adding features. Along the way it makes mistakes and I guide it through fixing them. Then when it is slow, I profile and guide it through optimizations. So in the end, it's code that I know very, very well. I could have written it but it…

Sounds like its faster to just write the code by hand
Post reply on HN