Creator of Things SWE / AI Enthusiast / Vibecoder / Gamedev
Joined May 2026
- Tweets1.1K
- Following926
- Followers237
- Likes3.2K
ThingsDev retweeted
Codex didn't publish your .env to cloudflare, YOU did. You are responsible for whatever clanker generates for you.
This is why YOU READ THE CODE. If you can't read the code, you hire someone who can.
Infra providers should stop bankrolling oopsies like this so people learn that when there is accountability, humans are needed.
FINALLY found how my key got leaked and got the $90,000 bill from google
Opus 5.5 said codex had PUBLISHED MY ****ING .ENV TO CLOUDFALRE PAGES ‼️
Meanwhile codex couldn't find anything, refused to explain itself and flagged my chat for cybersecurity risk lol
ThingsDev retweeted
if you are a programmer and you'd like to start a company it is helpful to internalize two big weaknesses you have
1. your instincts for anything outside programming are terrible. everything you believe is likely 100% backwards
2. you've always been treated like the smart person in the room so it will take you a very long time to understand #1
for me personally it took ~ 10 years before i started to be able to unwind this
ThingsDev retweeted
This is absolute proof that you SHOULD still read your code and that SWE has not been eaten by AI
Real production coding skills are still key in 2026
GPT 5.6 SOL CANNOT BE TRUSTED.
I woke up this morning and my MRR was down THOUSANDS of dollars.
My customers did not cancel. Code written by GPT 5.6 Sol canceled EVERY active Stripe subscription my business had. In 7 seconds. While I slept.
Fable 5 has never done this to me.
Fable 5 can be trusted with production.
GPT 5.6 cannot.
ThingsDev retweeted
To some extent, I understand the urge to "not read the code". Yeah, automation can be fun. Closing the loop entirely and removing the human even more can speed things up.
Spending that time on planning, working on specifications etc may be better.
I also agree: AI got much better (again) and will continue improving. And with proper input & context (existing codebase, plans, interfaces designed by you etc) there may be very little to review.
But I'm not sure if it's really nothing.
Catching some error, drift or simply something you overlooked when planning early can save you wasted tokens and unnecessary extra work later.
It's not a binary decision.
You don't have to ALWAYS read the ENTIRE code. And vice versa, you don't have to NEVER read ANY code.
It's the critical parts you care about. I do, at least.
Not saying that this can never change but as long as I can't anticipate everything and work with systems that may drift, I want to take a look at the code, too. Parts of it at least.
ThingsDev retweeted
“AI writes better code than I do” is a strange thing to say when you think about it.
AI was trained on a vast corpus of published code. It reflects the average of all that code.
So what you’re really saying is:
“My code is below average.”
