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

491–500 of 675 posts

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

#491

Post by samtp »

tptacek wrote: post #452
samtp wrote: post #420

Earlier quoted context omitted.

> One thing that has been frustrating me is that people rarely share their workflows after making big claims Good luck ever getting that. I've asked that about a dozen times on here from people making these claims and have never received a response. And I'm genuinely curious as well, so I will continue asking.

People share this stuff all the time. Kenton Varda published a whole walkthrough[1], prompts and all. Stories about people's personal LLM workflows have been on the front page here repeatedly over the last few months. What people aren't doing is proving to you that their workflows work as well as they say they do. You want proof, you can DM people for their rate card and see what that costs. [1] https://news.ycombina…

Thanks for sharing and that is interesting to read through. But it's still just a demo, not live production code. From the readme:

> As of March, 2025, this library is very new, prerelease software.

I'm not looking for personal proof that their workflows work as well as they say they do.

I just want an example of a project in production with active users depending on the service for business functions that has been written 1.5/2/5/10/whatever x faster than it otherwise would have without AI.

Anyone can vibe code a side project with 10 users or a demo meant to generate hype/sales interest. But I want someone to actually have put their money where their mouth is and give an example of a project that would have legal, security, or monetary consequences if bad code was put in production. Because those are the types of projects that matter to me when trying to evaluate people's claims (since those are what my paycheck actually depends on).

Do you have any examples like that?

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

#493

Post by _dain_ »

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 think it's human-written but meant to sound like GPT cliches. Deliberately laying it on thick, as a pisstake.

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

#494

Post by _dain_ »

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…

lmao well done. can't tell if it's the topvoted reply because people got the joke, or because they didn't.

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

#495

Post by timmytokyo »

tptacek wrote: post #365
timmytokyo wrote: post #344

Earlier quoted context omitted.

As if a compiler or linter is the sole arbiter of correctness.

Nobody said anything about "correctness". Hallucinations aren't bugs. Everybody writes bugs. People writing code don't hallucinate. It's a pretty obvious rhetorical tactic: everybody associates "hallucination" with something distinctively weird and bad that LLMs do. Fair enough! But then they smuggle more meaning into the word, so that any time an LLM produces anything imperfect, it has "hallucinated". No. "Hallucina…

Speaking of rhetorical tactics, that's an awfully narrow definition of LLM hallucination designed to evade the argument that they hallucinate.

If, according to you, LLMs are so good at avoiding hallucinations these days, then maybe we should ask an LLM what hallucinations are. Claude, "in the context of generative AI, what is a hallucination?"

Claude responds with a much broader definition of the term than you have imagined -- one that matches my experiences with the term. (It also seemingly matches many other people's experiences; even you admit that "everybody" associates hallucination with imperfection or inaccuracy.)

Claude's full response:

"In generative AI, a hallucination refers to when an AI model generates information that appears plausible and confident but is actually incorrect, fabricated, or not grounded in its training data or the provided context.

"There are several types of hallucinations:

"Factual hallucinations - The model states false information as if it were true, such as claiming a historical event happened on the wrong date or attributing a quote to the wrong person.

"Source hallucinations - The model cites non-existent sources, papers, or references that sound legitimate but don't actually exist.

"Contextual hallucinations - The model generates content that contradicts or ignores information provided in the conversation or prompt.

"Logical hallucinations - The model makes reasoning errors or draws conclusions that don't follow from the premises.

"Hallucinations occur because language models are trained to predict the most likely next words based on patterns in their training data, rather than to verify factual accuracy. They can generate very convincing-sounding text even when "filling in gaps" with invented information.

"This is why it's important to verify information from AI systems, especially for factual claims, citations, or when accuracy is critical. Many AI systems now include warnings about this limitation and encourage users to double-check important information from authoritative sources."

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

#496

Post by manmal »

theshrike79 wrote: post #460
mgfist wrote: post #145

Earlier quoted context omitted.

My biggest takeaway from using AI is that (1) for my day job, it doesn't make me super productive with creation, but it does help with discovery, learning, getting myself unstuck, and writing tedious code. (2) however, the biggest unlock is it makes working on side projects __immensely__ easier. Before AI I was always too tired to spend significant time on side projects. Now, I can see my ideas come to life (albeit w…

#2 is the reason I keep paying for Claude Code Pro. For 20 a month I can get my stupid tool and utility ideas from "it would be cool if I could..." to actual "works well enough for me" -tools in an evening - while I watch my shows at the same time. After a day at work I don't have the energy to start digging through, say, OpenWeather's latest 3.0 API and its nuances and how I can refactor my old code to use the new A…

Ghostty has native push notification support for Claude Code‘s „finished“ events.

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

#497

Post by belter »

kaonwarb wrote: post #490
belter wrote: post #476

Earlier quoted context omitted.

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?

False analogy.

I must comprehend code at the abstraction level I am working at. If I write Python, I am responsible for understanding the Python code. If I write Assembly, I must understand the Assembly.

The difference is that Compilers are deterministic with formal specs. I can trust their translation. LLMs are probabilistic generators with no guarantees. When an LLM generates Python code, that becomes my Python code that I must fully comprehend, because I am shipping it.

That is why productivity is capped at review speed, you can't ship what you don't understand, regardless of who or what wrote it.

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

#498

Post by tptacek »

timmytokyo wrote: post #495
tptacek wrote: post #365

Earlier quoted context omitted.

Nobody said anything about "correctness". Hallucinations aren't bugs. Everybody writes bugs. People writing code don't hallucinate. It's a pretty obvious rhetorical tactic: everybody associates "hallucination" with something distinctively weird and bad that LLMs do. Fair enough! But then they smuggle more meaning into the word, so that any time an LLM produces anything imperfect, it has "hallucinated". No. "Hallucina…

Speaking of rhetorical tactics, that's an awfully narrow definition of LLM hallucination designed to evade the argument that they hallucinate. If, according to you, LLMs are so good at avoiding hallucinations these days, then maybe we should ask an LLM what hallucinations are. Claude, "in the context of generative AI, what is a hallucination?" Claude responds with a much broader definition of the term than you have i…

What is this supposed to convince me of? The problem with hallucinations is (was?) that developers were getting handed code that couldn't possibly have worked, because the LLM unknowingly invented entire libraries to call into that don't exist. That doesn't happen with agents and languages with any kind of type checking. You can't compile a Rust program that does this, and agents compile Rust code.

Right across this thread we have the author of the post saying that when they said "hallucinate", they meant that if they watched they could see their async agent getting caught in loops trying to call nonexistent APIs, failing, and trying again. And? The point isn't that foundation models themselves don't hallucinate; it's that agent systems don't hand off code with hallucinations in it, because they compile before they hand the code off.

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

#499

Post by tptacek »

Quarrelsome wrote: post #488
tptacek wrote: post #474

Earlier quoted context omitted.

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…

Again, as you've acknowledged, there's a whole meme structure in the industry about what a "10x" programmer is. I did not claim that LLMs turn programmers into "10x programmers", because I do not believe in "10x" programmers to begin with. I'm not being defensive, I'm rebutting a (false) factual claim. It's very clearly false; you can just read the piece and see for yourself.

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

#500

Post by Wowfunhappy »

jdelman wrote: post #468
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…

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

Please stop assuming that every comment that includes an em dash is AI. Em dashes are very useful!
Post reply on HN