OpenAI Launches Codex: An Autonomous Programming Agent
AI and I16 Mai 2025

OpenAI Launches Codex: An Autonomous Programming Agent

OpenAI just launched Codex, a brand-new coding agent that can build features and fix bugs autonomously. We’ve been testing it at Every for a few days, and I’m impressed.


I invited Alexander Embiricos, a member of the OpenAI product staff responsible for Codex, to demo the agent live on a special edition of AI & I. We talk through:


  • What Codex is and how it works. Codex’s UI allows developers to see the list of tasks the agent is working on, how many lines were changed for each, and the status of the PR. It’s built for the senior software engineer who wants to delegate and review tasks efficiently.

  • How OpenAI is thinking about agents. Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes.

  • Why an “abundance mindset” is best for interacting with agents. Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task, like a difficult bug—it’s worth it even if only one of them succeeds.

  • OpenAI’s vision for the future of programming. In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding.


Timestamps:

  • Introduction: 00:00:52

  • The product decisions behind Codex’s interface: 00:01:40

  • How Codex works under the hood: 00:06:20

  • Why you need an abundance mindset to work well with agents: 00:14:06

  • Setting Codex to work on a real task in “Ask” mode: 00:16:28

  • How OpenAI is thinking about designing agents: 00:18:54

  • The future of programming is social: 00:31:16

  • Reviewing Codex’s work live: 00:37:21

  • How the landscape of agents will evolve: 00:39:41

  • Episoder(98)

    She Turned Her Whole Life Into Training Data—For an AI Baby

    She Turned Her Whole Life Into Training Data—For an AI Baby

    Sarah Rose Siskind is incubating two types of intelligence at once: her unborn child, and FetusGPT—an LLM trained on nothing but what she hears and says throughout the day.This includes Seinfeld episo...

    10 Des 20251h 13min

    Why Opus 4.5 Just Became the Most Influential AI Model

    Why Opus 4.5 Just Became the Most Influential AI Model

    The world changed last week—Opus 4.5 is the best coding model Dan has ever used.It can keep coding and coding autonomously without tripping over itself—and it marks a completely new horizon for the cr...

    3 Des 20251h 25min

    Best of the Pod: Would You Shut Down Your Most Successful Product? The Arc to Dia Story

    Best of the Pod: Would You Shut Down Your Most Successful Product? The Arc to Dia Story

    If you had millions of people using a product you spent years building, would you kill it?That’s exactly what The Browser Company did with Arc.Originally recorded in July before The Browser Company’s ...

    26 Nov 20251h 23min

     Best of the Pod: Claude Code - How Two Engineers Ship Like a Team of 15

    Best of the Pod: Claude Code - How Two Engineers Ship Like a Team of 15

    If you’re using AI to just write code, you’re missing out.Two engineers at Every shipped six features, five bug fixes, and three infrastructure updates in one week—and they did it by designing workflo...

    19 Nov 202553min

    Building AI Agents to Launch a Million Businesses

    Building AI Agents to Launch a Million Businesses

    Henrik Werdelin wants to launch a million businesses that each make $1M—and he’s doing it with AI.After helping launch Barkbox and Ro Health through his incubator Prehype, Henrik is distilling everyth...

    12 Nov 20251h 5min

    What Jason Fried Learned from 26 Years of Building Great Products

    What Jason Fried Learned from 26 Years of Building Great Products

    37signals makes tens of millions in profit every year but Jason Fried isn’t all that interested in running a business.Instead, he cares most about making great products—like Basecamp, HEY, and Ruby on...

    5 Nov 202558min

    How Salesforce Is Using AI to Power the Enterprise

    How Salesforce Is Using AI to Power the Enterprise

    This episode contains sponsored content in partnership with Salesforce.At Dreamforce 2025, Every CEO Dan Shipper sat down with Silvio Savarese, chief AI scientist at Salesforce, to discuss how one of ...

    31 Okt 202514min

    Inside Claude Code From the Engineers Who Built It

    Inside Claude Code From the Engineers Who Built It

    At Every, the team credits Claude Code with transforming the way they work.They now ship to codebases they barely know, each new feature makes the next easier to build, and even non-technical teammate...

    29 Okt 20251h 10min

    Populært innen Teknologi

    romkapsel
    rss-avskiltet
    tomprat-med-gunnar-tjomlid
    teknisk-sett
    nasjonal-sikkerhetsmyndighet-nsm
    energi-og-klima
    rss-impressions-2
    shifter
    elektropodden
    lydartikler-fra-aftenposten
    fornybaren
    hans-petter-og-co
    smart-forklart
    pedagogisk-intelligens
    rss-alt-vi-kan
    rss-ki-praten
    rss-fish-ships
    rss-tendencast-kunstig-intelligens-og-juss-2
    rss-heis
    rss-for-alarmen-gar