LessWrong (30+ Karma)

“The Codex of Ultimate Vibing” by Zvi

22 min • 21 maj 2025

While we wait for wisdom, OpenAI releases a research preview of a new software engineering agent called Codex, because they previously released a lightweight open-source coding agent in terminal called Codex CLI and if OpenAI uses non-confusing product names it violates the nonprofit charter. The promise, also reflected in a number of rival coding agents, is to graduate from vibe coding. Why not let the AI do all the work on its own, typically for 1-30 minutes?

The answer is that it's still early days, but already many report this is highly useful.

Introducing Codex

Sam Altman: today we are introducing codex.

it is a software engineering agent that runs in the cloud and does tasks for you, like writing a new feature of fixing a bug.

you can run many tasks in parallel.

it is amazing and exciting how much software one [...]

---

Outline:

(00:43) Introducing Codex

(04:24) System Card Addendum

(06:37) Update to Codex CLI

(07:50) Overall Reception

(09:36) Codex Offers Mundane Utility

(15:25) Codex Doesn't Offer Mundane Utility

(18:36) Our Price Cheap

(20:38) Two Kinds of Agent

---

First published:
May 20th, 2025

Source:
https://www.lesswrong.com/posts/z8FWLLjLHtKBENMi9/the-codex-of-ultimate-vibing

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Two graphs comparing performance metrics for SWE-Bench Verified and OpenAI tasks.

The left graph shows accuracy versus number of attempts, while the right bar graph displays accuracy percentages across different models, ranging from 11% to 75%.
Screenshot of safety and privacy settings explaining system operator safeguards.

The image shows a user interface information panel titled

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Senaste avsnitt

Podcastbild

00:00 -00:00
00:00 -00:00