# Fixing papercuts with Codex

## Метаданные

- **Канал:** OpenAI
- **YouTube:** https://www.youtube.com/watch?v=yHzfc1Ih7jw
- **Дата:** 16.05.2025
- **Длительность:** 2:49
- **Просмотры:** 66,348
- **Источник:** https://ekstraktznaniy.ru/video/11302

## Описание

See how OpenAI engineer Max Johnson can finally get to fixing papercuts, rather than letting them accumulate into tech debt. Read more about Codex, a cloud-based software engineering agent, in our blog: http://openai.com/index/introducing-codex/

## Транскрипт

### Segment 1 (00:00 - 02:00) []

So, I remember when there was this sort of web 2. 0 movement where people were like, "Wow, we can make websites interactive and more engaging and more like applications in and of themselves, but then of course there was a mobile paradigm where all of a sudden people had these computers in their pockets. So, those definitely stand out. Yeah, this feels like one of those kind of transcendent moments. My name is Max Johnson. I'm a software engineer here at OpenAI working on traptex. This is a special launch. I've never actually worked on a product that I felt as connected with as this one cuz I use it every day. It's solving a very real problem that I have in my work. When I'm working day-to-day, I'm constantly seeing problems with the code, little paper cuts, things that don't meet best practices, or maybe they're little bugs that maybe they matter, maybe they don't really matter, but may bite someone in the butt later on, you know, if we're not paying attention. And if I go down and try to solve all these problems myself in the moment, I would just never build anything new, right? Nothing would get done. With codeex, what's really cool is when I see these paper cuts, little problems, I don't have to break my attention. I can fire them off into codeex and come back to them in a you know 30 minutes or an hour when it's done and slowly over time the quality of the codebase goes up without any real additional investment of my attention and my time. Let me show you an example. So recently I was working on a piece of our code which is sort of a testing harness for our back end and I noticed the code had a few problems where I felt you know could be better but I don't know if they really rise to the level of me interrupting my main work starting a new branch a new PR just to fix these things. So instead I'll just fire them off into codeex. I see that there's a retry strategy here, but it looks like part of the logic was deleted as part of a refactor, which is unfortunate, but common. So, I'm going to go ahead and go over to codeex, and I'll just say in this file, it looks like there was a regression in the request JSON method retry implementation. I'll just say review the behavior from before the problem was introduced and then reintroduce that behavior and fix the bug. There's so much to build and these little chores sometimes feel like they're standing in the way of the more the most important and impactful work that we could be doing. And so being able to hand them off to a model is super empowering. I've never felt more engaged or excited to be an engineer than I do right now.