I cowboyed a lot of projects, then 2 years later a feature is not working as expected. It is.

Good docs, signed off by stake holders is essential. It basically covers you the dev, and confirms everyone involved agrees on what the software will do in certain situations.

I encountered bugs created by AI. No matter how many times it tried it could not fix the bug, it was introducing so much slop to work around the issue.

I finally gave up and read documentation for 15 minutes and solved the problem.

I will never push AI generated code to production without understanding it, and this is why I only generate small code snippets and copy/paste most of the time.

Writing code at enterprise level is insanely difficult. You are constrained by budget, staff, legacy databases/environments, business rules hiding all over the place, and people.

You can't just rewrite everything. So over many years people are touching small parts of the pie.

If it works it isn't low quality.

Yeah, enterprise code has that trope of being enterprise-y, verbose and bad. In my experience, that has always been the opposite. At the big corps/FAANGs I worked at, a single line of change can adversely impact millions of paying customers, so a lot of the verbosity and harnesses exists to dampen the failure modes. Most of the terribly written stuff has always been at startups, where devs fling nearly anything across the finish line, if it barely works the happy path.

> If it works it isn't low quality.

then the same applies to AI written code?

The code I have seen and see still, started shitty.

I have a blazor app in poduction, Codex made errors which it could not fix and it required me reading documentation. I won't argue that it didn't make my life simpler, tasks which would take me days are done in hours, sometimes without touching code.

Yea, i still deal with a ton of code in AI heavy workflows. If anything the frustrating part is absorbing the code quickly enough. AI (Claude for me) writes in cryptic text and the code flows can often be non-obvious.

I need (and am exploring) custom review tooling to improve this AI->Human code flow. Reviewing PRs were always the hardest part for me in programming. They were often full of the developers decisions and you have to rediscover those as you're reading code for it to make sense[1]. However i find this even more difficult to discover these decisions from AI.

However unlike human PRs we can ask more of AI. Rarely have i had a developer put on a presentation for a PR - but AI could right? AI could produce a guided walkthrough of the code. Not sure if it will help of course, but my thought is we're all stuck in the old "PR review flow" but instead of PRs it's AI - and the volume of them is far greater than anything prior. So i expect we need to tweak how we review, how we get information from LLMs.

[1]: I'm speaking generally, and about larger PRs. Not some small func where you can easily see what it does. Business logic and complex code can be difficult to decipher in PRs, imo.

I'm building https://pyor.review to fix this problem, try it out and let me know what you think.

We fight the clankers.

Oddly enough, this will be the most ORGANIC hacker news comment section in a while.

Stand up to clankers fellow humans!

What else are we going to do when LLMs are down? Need some fun in here.

My processing power was weak before LLM era, now it is extra weak.

I would write a clever comment, but chatGPT is down.

Do you have children?

While parents have some control, they don't have as much control as you think. It is a constant, "but my friends can do this", and you have to deal with it all the time.

Parents now have to work 2 jobs, so the kid spends most of their time outside of home.

Also, comparing FB to cars, doritos is not fair imo, FB is closer to crack. It can also be accessed on other devices than phones, WHICH they need for school. Not every parent knows how to block it, and kids find ways around road blocks anyway.

We are far too casual about addiction, and suits that endorse language like this are doing more harm to society’s rational appraisal of risks than good.

If your kid is addicted to crack cocaine, they have a problem that is light-years further down the road to existential harm than a similar problem with Doritos or social media.

>It is a constant, "but my friends can do this", and you have to deal with it all the time.

I don't have children, but I was a child and I know parents.

It's not a given that a child has this type of 2 way negotiation/bargaining power in the home, let alone the freedom to speak their mind towards their parents.