A Research Preview of Codex

Some engineers on my team at Assembled and I have been a part of the alpha test of Codex, and I'll say it's been quite impressive.

We’ve long used local agents like Cursor and Claude Code, so we didn’t expect too much. But Codex shines in a few areas:

Parallel task execution: You can batch dozens of small edits (refactors, tests, boilerplate) and run them concurrently without context juggling. It's super nice to run a bunch of tasks at the same time (something that's really hard to do in Cursor, Cline, etc.)

It kind of feels like a junior engineer on steroids, you just need to point it at a file or function, specify the change, and it scaffolds out most of a PR. You still need to do a lot of work to get it production ready, but it's as if you have an infinite number of junior engineers at your disposal now all working on different things.

Model quality is good, but hard to say it's that much better than other models. In side-by-side tests with Cursor + Gemini 2.5-pro, naming, style and logic are relatively indistinguishable, so quality meets our bar but doesn’t yet exceed it.

If you aren't hiring junior engineers to do these kinds of things, where do you think the senior engineers you need in the future will come from?

My kid recently graduated from a very good school with a degree in computer science and what she's told me about the job market is scary. It seems that, relatively speaking, there's a lot of postings for senior engineers and very little for new grads.

My employer has hired recently and the flood of resumes after posting for a relatively low level position was nuts. There was just no hope of giving each candidate a fair chance and that really sucks.

My kid's classmates who did find work did it mostly through personal connections.

Hiring of juniors is basically dead these days and it has been like this for about 10 years and I hate it. I remember when I was a junior in 2014 there were actually startups who would hire cohorts of juniors (like 10 at a time, fresh out of CS degree sort of folks with almost no applied coding experience) and then train them up to senior for a few years, and then a small number will stay and the rest will go elsewhere and the company will hire their next batch of juniors. Now no one does this, everyone wants a senior no matter how simple the task. This has caused everyone in the industry to stuff their resume, so you end up in a situation where companies are looking for 10 years of experience in ecosystems that are only 5 years old.

That said, back in the early 00s there was much more of a culture of everyone is expected to be self-taught and doing real web dev probably before they even get to college, so by the time they graduate they are in reality quite senior. This was true for me and a lot of my friends, but I feel like these days there are many CS grads who haven't done a lot of applied stuff. But at the same time, to be fair, this was a way easier task in the early 00s because if you knew JS/HTML/CSS/SQL, C++ and maybe some .NET language that was pretty much it you could do everything (there were virtually no frameworks), now there are thousands of frameworks and languages and ecosystems and you could spend 5+ years learning any one of them. It is no longer possible for one person to learn all of tech, people are much more specialized these days.

But I agree that eventually someone is going to have to start hiring juniors again or there will be no seniors.

The place where I work at hires an ungodly amount of juniors and fresh-grads (because a lot of them drop out and quit before they do any meaningful work). We're talking people that are completely unproductive and unusable for any sort of commercial project. We then spend at-least a year or two giving them a salary whilst they do toy projects and get trained. Literally doing what I remember doing in 1st/2nd year college with group projects and pet-assignments, complete with grades and feedback etc. Even after all of that, we still have to "train" them with hand-holding on an actual project work before they are a net-positive. Sooner or later someone will realize that they can just forego all that wasted training effort and just hire someone that is already productive. There is always a small percentage that are amazing and they get pushed through to projects very quickly. Which is a shame, because they then watch their fellow cohort sit around doing pet-projects and receive a salary, whilst they slog through a real project with deadlines, stress and the risk of failing.

This is entirely a combination of two things: The quality of grads coming out of college/university, and pressures coming from the market. Colleges have been pushing through entirely unqualified students, some even language illiterate, into the market place and what we're seeing is a response to that. Now couple that with the pressures that companies are facing, and you can see why none of them want to even take on the risk of training and up-skilling someone just so they can find the actual good employees which are a small percentage.

Of course, in my company's particular country and context, government regulations make it impossible to fire someone and there is huge pressure to keep-up DEI quotas despite no actual good DEI candidates being available, and we have a mess. Day to day is glorified baby-sitting people not-knowing what to do, dealing with their "feelings" (usually feelings of inadequacy and sometimes snobbish entitlement) and still trying complete a project at the same time.