Alex Embiricos

speaker

1,288 appearances 2 recordings 2 series first heard Feb 2026 last heard 21 Feb

Alex Embiricos’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 2 in all, peaking in Feb 2026 with 2.

Appearances

newest first · ▶ plays the moment

The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch · 20VC: Codex vs Claude Code vs Cursor: Who Wins, Who Loses | Will All Coding Be Automated - Do We Need PMs | The Real Bottleneck to AGI | The Three Phases of Agents and What You Need to Know with Alex Embiricos, Head of Codex at OpenAI · 21 Feb 2026 podcast

Then, OK, there's actual code review.

I think a problem that I hear a lot of people talking about, especially in the open source world, is a lot of AI slop.

People will just be submitting PRs to these open source repos, and they're trash.

And maybe the person submitting the PR hasn't even tested them or definitely hasn't reviewed the code.

I think this is a problem.

And so a common practice with Codex is to have Codex review its own PR or its own change.

And Codex is actually incredibly good at this.

We've explicitly trained the model to be good at code review.

And that included things like making sure it's really good at creating high signal feedback.

So it'll basically have few false positives of criticism, which means you can really trust when it has feedback.

And so not only do we encourage people on the team and elsewhere to just ask Codex to review, you can then also set it up to just automatically review.

So nearly all code at OpenAI is reviewed by Codex automatically whenever you push it to a Git repo.

Actually, one fun thing for people who haven't tried Codex yet or didn't try it recently, sometimes the way that people see how good our models are is by asking Codex to review a different model's code.

And basically they're like, oh, shoot, I should probably just be using Codex to write my code in general.

We've taken this kind of counterintuitive approach with Codex to just build it super openly.

So the Codex core harness is open source, and we're always trying to make it easier for people to switch.

So for instance, when we first launched Codex last year, we created, like, created is even a heavy word.

We just established a convention, which is called agents.md.

This is basically a file that you can put instructions for the agent in.

And we didn't call it codex.md.

Showing 201–220 of 1,288 · page 11 of 65