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

Things that helped me get out of the AI 10x engineer imposter syndrome

colton.dev

Post reply on HN
Print view View original

481–490 of 675 posts

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#481

Post by jdelman »

dehugger wrote: post #470
jdelman wrote: post #468

Earlier quoted context omitted.

Speaking of irony... did ChatGPT help you write this comment?

It doesn't read to me like AI content. It's also against HN guidelines to randomly suggest comments are AI generated.

I definitely didn't "randomly" suggest it, unless you're suggesting all human actions are the result of randomness. I also just re-read the guidelines and I didn't see anything about in the letter of the law, but I agree it probably goes against the spirit. I'll take the downvotes and keep it to myself next time.

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#482

Post by coltonv »

kasey_junk wrote: post #449
coltonv wrote: post #426

Earlier quoted context omitted.

What I'm saying is that the model will get into one of these loops where it needs to be killed, and I'll look at some of the intermediate states and the reasons for failure and they are because it hallucinated things, ran tests, got an error. Does that make sense? Deleting and re-prompting is fine. I do that too. But even one cycle of that often means the whole prompting exercise takes me longer than if I just wrote…

I think maybe this is another disconnect. A lot of the advantage I get does not come from the agent doing things faster than me, though for most tasks it certainly can. A lot of the advantage is that it can make forward progress when I can’t. I can check to see if an agent is stuck, and sometimes reprompt it, in the downtime between meetings or after lunch before I start whatever deep thinking session I need to do. T…

I've done a few of these types of hands off and go to a meeting style interactions. It has worked a few times, but I tend to just find that they over do it or cause issues. Like you ask them to fix an error and they add a try catch, swallow the error, and call it a day. Or the PR has 1000 line changes when it should have two.

Either way, I'm happy that you are getting so much out of the tools. Perhaps I need to prompt harder, or the codebase I work on has just deviated too much from the stuff the LLMs like and simply isn't a good candidate. Either way, appreciate talking to you!

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#483

Post by antonvs »

bluefirebrand wrote: post #397
antonvs wrote: post #272

Earlier quoted context omitted.

Are you boycotting AI or something? If you try it yourself you'll soon find out that the answer is a very obvious yes. You don't need a paid plan to benefit from that kind of assistance, either.

> Are you boycotting AI or something? At this point I am close to deciding to fully boycott it yes > If you try it yourself you'll soon find out that the answer is a very obvious yes I have tried plenty over the years, every time a new model releases and the hype cycle fires up again I look in to see if it is any better I try to use it a couple of weeks, decide it is overrated and stop. Yes it is improving. No it is…

You asked whether it's really better than "what we already had with search engines, online documentation and online Q&A sites".

How have you found it not to be significantly better for those purposes?

The "not good enough for you to trust" is a strange claim. No matter what source of info you use, outside of official documentation, you have to assess its quality and correctness. LLM output is no different.

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#484

Post by sellmesoap »

edm0nd wrote: post #175
mavamaarten wrote: post #101

Earlier quoted context omitted.

Yeah. I just need to babysit it too much. Take copilot, it gives good suggestions and blows me away sometimes with a block of code which is exactly what I'd type. But actively letting it code (at least with gpt4.1 or gpt4o) just doesn't work well enough for me. Half of the time it doesn't even compile, and after fixing that it's just not really correctly working either. I'd expect it to work like a very junior progra…

>I'd expect it to work like a very junior programmer, but it works like a very drunk senior programmer that isn't listening to you very well at all. This seems to be the current consensus. A very similar quote from another recent AI article: One host compares AI chatbots to “a very smart assistant who has a dozen Ph.D.s but is also high on ketamine like 30 percent of the time.” https://lithub.com/what-happened-when-i…

To be fair I've known 10x developers who are high on ketamine 100 percent of the time, it boggles my mind that this can work.

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#485

Post by kazinator »

rhines wrote: post #475
torginus wrote: post #459

Earlier quoted context omitted.

I now understand what artists felt when seeing stable diffusion images - AI code is often just wrong - not in the moral sense, but it contains tons of bugs, weirdness, excess and peculiarities you'd never be happy to see in a real code base. Often getting rid of all of this, takes comparable amount of time as doing the job in the first place. Now I can always switch to a different model, increase the context, prompt…

The comparison to art is apt. Generated art gets the job done for most people. It's good enough. Maybe it's derivative, maybe there are small inaccuracies, but it is available instantly for free and that's what matters most. Same with code, to many people. And the knock-on effect is that there is less menial work. Artists are commissioned less for the local fair, their friend's D&D character portrait, etc. Programmer…

Artistic paintings are not technical artwork like computer programs or circuit boards. Nothing falls down if something is out of place.

A schematic of a useless amplifier that oscillates looks just as pretty as one of a correct amplifier. If we just want to use it as a repeated print for the wallpaper of an electronic lab, it doesn't matter.

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#486

Post by kazinator »

coltonv wrote: post #450
voxleone wrote: post #447

There’s something ironic here. For decades, we dreamed of semi-automating software development. CASE tools, UML, and IDEs all promised higher-level abstractions that would "let us focus on the real logic." Now that LLMs have actually fulfilled that dream — albeit by totally different means — many devs feel anxious, even threatened. Why? Because LLMs don’t just autocomplete. They generate. And in doing so, they challe…

Very interesting perspective. Thanks for sharing!

Let's connect on HackedIn!

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#487

Post by zaptheimpaler »

voxleone wrote: post #447

There’s something ironic here. For decades, we dreamed of semi-automating software development. CASE tools, UML, and IDEs all promised higher-level abstractions that would "let us focus on the real logic." Now that LLMs have actually fulfilled that dream — albeit by totally different means — many devs feel anxious, even threatened. Why? Because LLMs don’t just autocomplete. They generate. And in doing so, they challe…

I think if you're paying any attention to the state of the world, you can see labor is getting destroyed by capital - bad wages, worse working conditions including more surveillance, metrics everywhere, immoral companies, short contracts and unstable companies/career paths, increasing monopolization and consolidation of power. We were so insulated from this for so long that it's easy to not really grasp how bad things are for most workers. Now the precarity of our situation is dawning on us.

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#488

Post by Quarrelsome »

tptacek wrote: post #474
Quarrelsome wrote: post #458

Earlier quoted context omitted.

10x is a meme in our industry that relates to developer productivity and I think it well reflects the sort of productivity gain that someone would be "nuts" to be skeptical about. You might not have specifically said "10x" but I imagine many people left your article believing that agentic AI is the "next 10x" productivity boost. They used it 25 times in their piece and in your piece stated that being interested in "t…

No. There's all sorts of software engineering craft that usually has no place on the job site; for instance, there's a huge amount of craft in learning pure-functional languages like Haskell, but nobody freaks out when their teams decide people can't randomly write Haskell code instead of the Python and Rust everyone else is writing. You're extrapolating because you're trying to defend your point, but the point you'r…

Sure, I'm extrapolating what I read as strong language in your article as being a direct attack on making the code precise and flexible over good enough to ship (mediocre code, first-pass, etc). I imagine this might continue to be a battleground as adoption increases, especially at orgs with less engineering culture, in order to drive down costs and increase agentic throughput.

However there is a bit of irony in that you're happy to point out my defensiveness as a potential flaw when you're getting hung up on nailing down the "10x" claim with precision. As an enjoyer of both articles I think this one is a fair retort to yours, so I think it a little disappointing to get distracted by the specifics.

If only we could accurately measure 1x developer productivity, I imagine the truth might be a lot clearer.

Re: Things that helped me get out of the AI 10x engineer imposter syndrome

#490

Post by kaonwarb »

belter wrote: post #476
voxleone wrote: post #447

There’s something ironic here. For decades, we dreamed of semi-automating software development. CASE tools, UML, and IDEs all promised higher-level abstractions that would "let us focus on the real logic." Now that LLMs have actually fulfilled that dream — albeit by totally different means — many devs feel anxious, even threatened. Why? Because LLMs don’t just autocomplete. They generate. And in doing so, they challe…

You miss the fundamental constraint. The bottleneck in software development was never typing speed or generation, but verification and understanding. Even if LLMs worked perfectly without hallucinations (they don't and might never), a conscientious developer must still comprehend every line before shipping it. You can't review and understand code 10x faster just because an LLM generated it. In fact, reviewing generat…

> Even if LLMs worked perfectly without hallucinations (they don't and might never), a conscientious developer must still comprehend every line before shipping it.

This seems excessive to me. Do you comprehend the machine code output of a compiler?

Post reply on HN