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

41–50 of 675 posts

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

#41

Post by tempodox »

jf22 wrote: post #2

> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…

So you're not a developer any more but a tenant who pays rent. Speaking of which, I have a bridge to sell you…

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

#42

Post by simpaticoder »

The expectations are higher than reality, but LLMs are quite useful in many circumstances. You can characterize their use by "level of zoom", from "vibe coding" on the high end, to "write this function given its arguments and what it should return" at the low end. The more 'zoomed in' you are, the better it works, in my experience.

Plus there are use-cases for LLMs that go beyond augmenting your ability to produce code, especially for learning new technologies. The yield depends on the distribution of tasks you have in your role. For example, if you are in lots of meetings, or have lots of administrative overhead to push code, LLMs will help less. (Although I think applying LLMs to pull request workflow, commit cleanup and reordering, will come soon).

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

#44

Post by tptacek »

This article sets a ludicrous bar ("10x"), then documents the author's own attempt over some indeterminate time to clear that bar. As a result, the author has classified all the AI-supporters in the industry into three categories: (1) people who are wrong in good faith, (2) people who are selling AI tools, and (3) evil bosses trying to find leverage in programmer anxiety.

That aside: I still think complaining about "hallucination" is a pretty big "tell".

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

#45

Post by micahscopes »

symfrog wrote: post #6
jf22 wrote: post #2

> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…

Do you have a link to some of the code that you have produced using this approach? I am yet to see a public or private repo with non-trivial generated code that is not fundamentally flawed.

This one was a huge success:

https://github.com/micahscopes/radix_immutable

I took an existing MIT licensed prefix tree crate and had Claude+Gemini rewrite it to support immutable quickly comparable views. The execution took about one day's work, following two or three weeks thinking about the problem part time. I scoured the prefix tree libraries available in rust, as well as the various existing immutable collections libraries and found that nothing like this existed. I wanted O(1) comparable views into a prefix tree. This implementation has decently comprehensive tests and benchmarks.

No code for the next two but definitely results...

Tabu search guided graph layout:

https://bsky.app/profile/micahscopes.bsky.social/post/3luh4d...

https://bsky.app/profile/micahscopes.bsky.social/post/3luh4s...

Fast Gaussian blue noise with wgpu:

https://bsky.app/profile/micahscopes.bsky.social/post/3ls3bz...

In both these examples, I leaned on Claude to set up the boilerplate, the GUI, etc, which gave me more mental budget for playing with the challenging aspects of the problem. For example, the tabu graph layout is inspired by several papers, but I was able to iterate really quickly with claude on new ideas from my own creative imagination with the problem. A few of them actually turned out really well.

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

#46

Post by zwnow »

rob_c wrote: post #16
symfrog wrote: post #6

Earlier quoted context omitted.

Do you have a link to some of the code that you have produced using this approach? I am yet to see a public or private repo with non-trivial generated code that is not fundamentally flawed.

That's disingenuous or naive. Almost nobody decides to expressly highlight the section of code (or whole files generated by ai) they just get on with the job when there's real deadlines and it's not about coding for the sake of the art form...

Same as pretending that vibe coding isn't producing tons of slop. "Just improve your prompt bro" doesn't work for most real codebases. The recent TEA app leak is a good example of vibe coding gone wrong, I wish I had as much copium as vibe coders to be blind to these things, as most of them clearly are like "it happened to them but surely won't happen to ME."

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

#47

Post by neutronicus »

jf22 wrote: post #2

> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…

Yeah that fucker Claude is tireless when it comes to checking return types, checking for null, etc etc

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

#48

Post by adolph »

Those who are not aware of the mythical man month's silver bullet are condemned to rewrite it.

  The amount of product ideation, story point negotiation, bugfixing, code 
  review, waiting for deployments, testing, and QA in that go into what was 
  traditionally 3 months of work is now getting done in 7 work days? For that 
  to happen each and every one of these bottlenecks has to also seen have 10x 
  productivity gains.

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

#49

Post by micahscopes »

r3trohack3r wrote: post #29
jf22 wrote: post #2

> What LLMs produce is often broken, hallucinated, or below codebase standards. With enough rules and good prompting this is not true. The code I generate is usually better than what I'd do by hand. The reason the code is better all the extra polish and gold plating is essentially free. Everything I generate comes out commented great error handling, logging, SOLID, and united tested using established patterns in the…

I do think a lot of the discourse in this space can be summed up as: people are arguing about two non-overlapping segments of a distribution having no idea the other segment even exists; instead they just assume the other side is [hype/pessimistic].

It makes me wince a little

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

#50

Post by recursive »

echelon wrote: post #23
the__alchemist wrote: post #7

Earlier quoted context omitted.

I am pattern matching your last statement with what I've seen with my teammates who are more AI-oriented: I suspect this is a matter of making the metrics the goal. I would rather maintain something that is simple, works, and have targeted comments than something messy that meets the metrics you list.

I don't get all the prompt vibe coding going around. I don't use prompts to generate code. I use "tab-tab" auto complete to speed through refactorings and adding new fields / plumbing. It's easily a 3x productivity gain. On a good day it might be 10x. It gets me through boring tedium. It gets strings and method names right for languages that aren't statically typed. For languages that are statically typed, it's still…

I use tab auto complete, and i think it's a 5% productivity gain. On a good day, maybe 10%. I haven't put much effort into optimizing the setup or learning advanced usage patterns or anything. I'm using stock copilot, provided by my employer. If I had to pay for it, I wouldn't be using it, as it doesn't justify the cost.
Post reply on HN