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

151–160 of 675 posts

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

#151

Post by jf22 »

reactordev wrote: post #5
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…

Let’s talk about rules and docs, shall we? What makes a good rule for AI to keep it on task? What are your setups for docs and attaching them to the context (do you need to? Or just the location?) Let’s boil this down to an easy set of reproducible steps any engineer can take to wrangle some sense from their AI trip.

There are tons of these guides around the internet. I'm only using what other people have already published.

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

#152

Post by jf22 »

apwell23 wrote: post #70
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…

> With enough rules and good prompting this is not true. There are atleast 10 posts on HN these days with the same discussion in circle. 1. AI sucks at code 2. you are not using my magic prompting technique

It's not magic. The techniques are well established and widely shared.

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

#153

Post by jf22 »

tempodox wrote: post #41
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…

I'm not even sure what this is supposed to say.

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

#154

Post by logicchains »

hyperbovine wrote: post #90
simonw wrote: post #77

I found myself agreeing with quite a lot of this article. I'm a pretty huge proponent for AI-assisted development, but I've never found those 10x claims convincing. I've estimated that LLMs make me 2-5x more productive on the parts of my job which involve typing code into a computer, which is itself a small portion of that I do as a software engineer. That's not too far from this article's assumptions. From the artic…

This is (I think) a reference to the 10x engineer, another myth of which I have always been highly dubious ( https://www.simplethread.com/the-10x-programmer-myth/ ).

You don't believe Fabrice Bellard exists?

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

#155

Post by mgfist »

Izkata wrote: post #122
hyperbovine wrote: post #90

Earlier quoted context omitted.

This is (I think) a reference to the 10x engineer, another myth of which I have always been highly dubious ( https://www.simplethread.com/the-10x-programmer-myth/ ).

10x sounds nice which is probably why it stuck, but it came from actual research which found the difference was larger than 10x - but also they were measuring between best and worst, not best and average as it's used nowadays. https://www.construx.com/blog/productivity-variations-among-...

All of this is hard to quantify. How much better than the average engineer is John Carmack, or Rob Pike or Linus? I consider myself average-ish and I don't think there's any world in which I could do what those guys did no matter how much time you gave me (especially without the hindsight knowledge of the creations). So I'd say they're all infinitely better than me.

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

#156

Post by ajaisibsbz »

rob_c wrote: post #40
shortrounddev2 wrote: post #19

I dont use ai code generation tools, I just use claude as a search engine. It hasn't changed the output rate of my code but I believe that its improved the quality of it by exposing me to patterns and features that I otherwise may not have. I used to take a very object oriented approach to code, but when I would ask claude to look at my code and critique it, it would often lead me into more functional patterns, with…

> I dont use ai code generation tools Then unfortunately you're leaving yourself at a serious disadvantage. Good for you if you're able to live without a calculator, but frankly the automated tool is faster and leaves you less exhausted so you should be taking advantage of it.

Is typing speed a bottle neck for people? Because otherwise you’re offloading thinking to the LLM. Unless you can understand code faster than you can write it (which I’ve never experienced - best case scenario I can understand as fast as I read).

As a junior I used to think it was ok to spend much less time on the review than the writing, but unless the author has diligently detailed their entire process a good review often takes nearly as long. And unsurprisingly enough working with an AI effectively requires that detail in a format the AI can understand (which often takes longer than just doing it).

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

#157

Post by mrbungie »

jf22 wrote: post #137
mrbungie wrote: post #21

Earlier quoted context omitted.

> The code I generate is usually better than what I'd do by hand. I'm always baffled by this. If you can't do it that well by hand, how can you discriminate its quality so confidently? I get there is a artist/art consumer analogy to be made (i.e. you can see a piece is good without knowing how to paint), but I'm not convinced it is transferrable to code. Also, not really my experience when dealing with IaC or (comple…

I can do it by hand but it takes time. With AI the extra quality and polish is basically free and instantaneous.

Ah, alright, that makes a lot more sense, like another poster said I read "'d" as "could".

Point still remains for junior and semi-senior devs though, or any dev trying to leap over a knowledge barrier with LLMs. Emphasis on good pipelines and human (eventually maybe also LLM based) peer-reviews will be very important in the years to come.

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

#158

Post by coltonv »

tptacek wrote: post #125
BoxFour wrote: post #88

Earlier quoted context omitted.

> I still think complaining about "hallucination" is a pretty big "tell". The conversation around LLMs is so polarized. Either they’re dismissed as entirely useless, or they’re framed as an imminent replacement for software developers altogether. Hallucinations are worth talking about! Just yesterday, for example, Claude 4 Sonnet confidently told me Godbolt was wrong wrt how clang would compile something (it wasn’t).…

That's not what people mean when they bring up "hallucinations". What the author apparently meant was that they had an agent generating Terraform for them, and that Terraform was broken. That's not surprising to me! I'm sure LLMs are helpful for writing Terraform, but I wouldn't expect that agents are at the point of being able to reliably hand off Terraform that actually does anything, because I can't imagine an age…

With terraform, using a property or a resource that doesn't exist is effectively the same as an API call that does not exist. It's almost exactly the same really, because under the hood terraform will try to make a gcloud/aws API call with your param and it will not work because it doesn't exist. You are making a distinction without a difference. Just because it can be caught at runtime doesn't make it insignificant.

Anyway, I still see hallucinations in all languages, even javascript, attempting to use libraries or APIs that do not exist. Could you elaborate on how you have solved this problem?

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

#160

Post by jsnell »

> 10x productivity means ten times the outcomes, not ten times the lines of code. This means what you used to ship in a quarter you now ship in a week and a half.

Not really? That's defining productivity as latency, but it's at least as valid to define productivity as throughput.

And then all the examples that are just about time spent waiting become irrelevant. When blocked waiting on something external, you just work on other things.

Post reply on HN