Things that helped me get out of the AI 10x engineer imposter syndrome
1–10 of 675 posts
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#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 code base.
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#3> 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 agree. With plenty of prompts (leave them in documents) you can get pretty good results.
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#4> 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…
Easily 99% of comments generated by LLMs are useless.
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#5> 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.
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#6> 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.
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#7> 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 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.
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#8> 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…
Can you point to an example repo with enough rules and good prompts?
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#9> 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…
Easily 99% of comments generated by LLMs are useless.
They're often repetitive if you're reading the code, but they're useful context that feeds back into the LLM. Often once the code is clear enough I'll delete them before pushing to production.
Re: Things that helped me get out of the AI 10x engineer imposter syndrome
#10> 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…
Easily 99% of comments generated by LLMs are useless.
I've noticed this too. They are often restatements of the line in verbal form, or intended for me, the LLM-reader about the prompt, vice a code maintainer.