Loading video...

Video Failed to Load

Go Home

If you use Codex, Tibo needs no introduction. We talked 100% about Codex (fun fact: he started building it!), and 0% about resets. Timestamps: 00:00 Intro 07:21 Working at Google 12:41 What drew Tibo to OpenAI 15:19 The early days of Codex 18:20 Why Codex was built in Rust...

81,634 views • 1 month ago •via X (Twitter)

26 Comments

Gergely Orosz's profile picture
Gergely Orosz1 month ago

Also watch or listen: • YouTube: • Spotify: • Apple:

jhey ʕ•ᴥ•ʔ's profile picture
jhey ʕ•ᴥ•ʔ1 month ago

@thsottiaux gonna throw this in the ears tomorrow 🙏 ??:??:?? How Tibo is able to keep granting codex usage limit resets

Edwin's profile picture
Edwin1 month ago

@thsottiaux Loved this episode! Great to see Rust still going strong.

serx · fireply.ai's profile picture
serx · fireply.ai1 month ago

@thsottiaux harness plays nice with other models but somehow never with your rate limit

kodenark's profile picture
kodenark1 month ago

@thsottiaux I think it’s fair to say we all love @thsottiaux

Eamon O'Callaghan's profile picture
Eamon O'Callaghan1 month ago

@thsottiaux Awesome guest, can't wait to listen to this one! You've had some banger episodes lately, keep it up!

Leo builds's profile picture
Leo builds1 month ago

@thsottiaux I really want to watch this interview with our favorite reset guy. 😊 Thank you!

Baron Hakkinen's profile picture
Baron Hakkinen1 month ago

@thsottiaux I see 'sponsored by turbopuffer' → I press ignore. Those guys are promoting their BS platform everywhere using all kinds of shady techniques.

AriesTheCoder's profile picture
AriesTheCoder1 month ago

@thsottiaux Will watch later... gonna go touch grass for now.

Silent Developer⭐|'s profile picture
Silent Developer⭐|1 month ago

@thsottiaux Watched the whole thing this morning - the part where Tibo says the early Codex days were mostly guesswork about what devs actually wanted hit home. Did building it teach you anything about tool design you couldn't have guessed before shipping?

Alvin De Cruz's profile picture
Alvin De Cruz1 month ago

@thsottiaux He looks really tired after hitting all the reset buttons

Dang's profile picture
Dang1 month ago

@thsottiaux The interesting bit is that Codex was built around the harness, not jusess owns the loop, model swaps stop being a rewrite. That’s the part most “agent” demos politely hide.

JustForFUNFUNFUN's profile picture
JustForFUNFUNFUN1 month ago

@thsottiaux Tibo never laugh. weird.

Andrea Postiglione's profile picture
Andrea Postiglione1 month ago

@thsottiaux The early history matters because it separates the constraints that shaped Codex from the capabilities we now project onto coding agents. I’m curious which limitation most influenced the current workflow of letting the agent act, then reviewing its work.

Silent Developer⭐|'s profile picture
Silent Developer⭐|1 month ago

@thsottiaux Your surveys catch what dashboards miss: policy versus practice. One split that never gets published: AI coding tool usage by seniority. Does your data show juniors shipping faster while seniors review more?

安叫兽|Bird🕊️ 🔶 BNB's profile picture
安叫兽|Bird🕊️ 🔶 BNB1 month ago

@thsottiaux 最想听 Rust 和开源那两段,Codex 早期也太有意思了

Abhijit Rawool's profile picture
Abhijit Rawool1 month ago

@thsottiaux the useful part of these conversations is the design intent behind the defaults. understanding why delegation, isolation, and verification work the way they do helps builders use the product better than another feature list.

Bagdex's profile picture
Bagdex1 month ago

@thsottiaux Can’t wait to watch the Gergely Orosz interview on Codex and OpenAI. Thanks, reset legend!

Vasu Bhardwaj's profile picture
Vasu Bhardwaj1 month ago

@thsottiaux The Reset Dealer himself!

D@RWIN's profile picture
D@RWIN1 month ago

@thsottiaux Who is Tibo?

Sofi a.'s profile picture
Sofi a.1 month ago

@thsottiaux Interesting perspective

Voxlessa's profile picture
Voxlessa1 month ago

@thsottiaux 0% resets is an impressive feat for a Codex interview this week. The early-days section sounds like a good place to start.

Andrew's profile picture
Andrew1 month ago

@thsottiaux Guaranteed banger. Gotta watch this

Sebastian Buzdugan's profile picture
Sebastian Buzdugan1 month ago

@thsottiaux codex adoption now hinges on sandbox reliability more than model quality, was that clear early

Josh Jackson | AI agent security's profile picture
Josh Jackson | AI agent security1 month ago

@thsottiaux The section on other models caught my eye. I'd want to know how much of the workflow survives a model swap without having to rewrite all the instructions.

Sofia w,'s profile picture
Sofia w,1 month ago

@thsottiaux Totally agree with this

Related Videos

Three months ago, Codex was trash for knowledge work. Now it's my daily driver. I use it for writing, recruiting, deep engineering work, and everything in between. It even keeps me at inbox 0. I chatted with Every 🧱's head of growth Austin Austin Tedesco on Every 🧱's AI & I about what changed, and why he now spends 80% of his working time in the Codex desktop app too. We get into: - How Codex went from making Austin feel like an idiot to being the place he goes to get stuff done, including complex tasks like writing go-to-market plans using existing material from Slack, Notion, and meeting transcripts. - Why the Codex’s desktop app, which is faster and more reliable than Claude Desktop/Cowork, is the real differentiator. - How I source candidates with Codex by having it identify career arcs, not keywords—my go-to move is identifying organizations likely to teach the skills Every needs for a role, and then find candidates from that pool who have since gone on to work in AI. This is a must-watch for anyone who's wondering whether it’s finally time to give Codex a try. Watch below! Timestamps How Codex went from a tool for senior engineers to a daily driver for knowledge work: 00:00:57 How Claude Code proved that a great coding agent works for any knowledge work: 00:02:42 Austin's switch to Codex: 00:07:24 How Austin set up Codex with folders, keys, and reviewer agents: 00:13:48 Using Codex to brainstorm automations across Gmail, Slack, and Notion: 00:18:24 How Austin manages the human review step when Codex is drafting communications: 00:22:42 Using Codex to build specialized agents inspired by product executive Claire Vo: 00:28:54 Synthesizing meeting transcripts and Slack threads into a go-to-market plan: 00:31:09 Building a live KPI tracker in Notion that agents can read: 00:40:15 Using Codex for recruiting: 00:44:54

Dan Shipper 📧

55,561 views • 5 months ago

OpenAI’s hottest app isn’t ChatGPT—it’s Codex. In the last few weeks alone, the Codex team shipped a desktop app, GPT-5.3 Codex (a new flagship model), and Spark, the fastest coding model I’ve ever used. Usage has grown fivefold since January and over a million people now use Codex weekly. Codex was also the app that OpenAI chose to run an ad for in the Super Bowl. I talked to Thibault (Tibo), head of Codex, and Andrew (Andrew Ambrosino), a member of technical staff who built the Codex app, for Every 📧’s AI & I about what OpenAI is building and how they’re using it internally. We get into: - Why they built a GUI instead of a terminal. Terminals work for quick tasks, they say, but feel limiting when you’re running multiple agents in parallel. The IDE, meanwhile, overwhelms users—and the Codex team wants the AI to dynamically decide which tools to show you for a given task. - How they’re teaching the model to read between the lines. Codex is great at following instructions, but optimize too hard in that direction, and it starts taking you literally—like copying a typo directly into the code. The team obsesses over this tradeoff, and is also introducing “personalities,” modes users can toggle between that control how blunt or supportive the model feels. - How OpenAI uses its own coding agent. Codex lets you schedule prompts to run on a recurring basis, and the team has dozens of automations running at all times. For example, one scans for merge conflicts every couple of hours so code is always ready to ship, and another picks a random file from the codebase multiple times a day and hunts for bugs no one would've gone looking for. - Why speed is a dimension of intelligence. OpenAI’s newest model (Spark) is so fast that they actually slow it down so you can read the output. They see the speed enabling three things: staying super in the flow, replacing brittle developer tools with intelligent ones that can adapt on the fly, and redirecting the model mid-task— especially with voice—so coding starts to feel more and more like a conversation. - Code review is the next bottleneck. Models can generate code faster than ever, but someone still has to verify that it works. The team is exploring a future where the model proves its own fix works—retracing the click path a user would take, screenshotting the results, and attaching the evidence to a pull request. This is a must-watch for anyone who uses AI coding agents—and is curious about the future of programming. Watch below! Timestamps: Introduction: 00:01:27 OpenAI’s evolving bet on its coding agent: 00:05:27 The choice to invest in a GUI (over a terminal): 00:09:42 The AI workflows that the Codex team relies on to ship: 00:20:38 Teaching Codex how to read between the lines: 00:26:45 Building affordances for a lightening fast model: 00:28:45 Why speed is a dimension of intelligence: 00:33:15 Code review is the next bottleneck for coding agents: 00:36:30 How the Codex team positions against the competition: 00:41:24

Dan Shipper 📧

15,588 views • 8 months ago

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. 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. 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. 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. Watch below!

Dan Shipper 📧

145,487 views • 1 year ago

.Natalia rode so hard for Claude Code we devoted an episode to how she was using it to automate her job running Every 📧’s consulting practice. Fast forward to five months later, and she rides just as hard for Codex. I had her back on AI & I to talk about what caused her to make the switch, including how she ran a prompt in Codex before bed and woke up to a finished, custom CRM tool. We get into: - Why she finds Codex easier to use than Claude Code - How she’s using loops in Codex to create customized tools that work exactly how she needs them to - Why the consulting team still pays for SaaS products like Attio and Asana even though they could vibe code their own versions - How she built an app to manage her father’s medical care in Codex - How knowledge work is evolving from sculpting to gardening, in which you develop the context and logic you need for an agent to execute for you This is a must-watch for anyone trying to figure out whether to build their own tools or buy real software—and what it takes to get an AI agent to run unsupervised for hours and nail the output. Watch below! Timestamps 1. Introduction: 00:01:05 2. How Natalia manages Claudie, the consulting team’s AI project manager: 00:02:35 3. Why the consulting team still pays for SaaS products: 00:04:55 4. Codex as a game changer : 00:11:47 5. Building personalized learning guides and illustrated explainers with AI: 00:14:55 6. Inside Natalia's AI-powered email triage system: 00:21:40 7. The shift from knowledge work as sculpting to knowledge work as gardening: 00:26:44 8. Using Codex to on-shot a custom CRM: 00:28:57 9. Using Codex to build an app that coordinates her father’s medical care: 00:33:16

Dan Shipper 📧

25,701 views • 3 months ago