If you use Codex, @thsottiaux 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 21:15 Why Codex is open source 25:50 Codex plays nice with other models: why? 32:09 How the harness works 36:44 Harness and model improvements 41:19 The SDLC behind Codex 46:39 Code reviews at Codex 52:09 Maintenance and architecture 56:43 How AI tools expand what engineers can do 1:02:30 The Merge: ChatGPT + Codex 1:07:16 How Tibo uses Codex and ChatGPT 1:10:44 Advice for engineers who want to work in AI

Brought to you by:

• @turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable. https://turbopuffer.com/pragmatic

• @AntithesisHQ – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages. https://antithesis.com/pragmatic

• @EntireHQ – Git hosting, rebuilt for the agentic era. Entire hosts your code in-region, and is up to 89x faster than any other competitor. https://entire.io/pragmatic

Oh, and to those still reading and wondering about resets: there was one yesterday already 😅

turbopuffer x Pragmatic Engineer

Source: https://turbopuffer.com/pragmatic turbopuffer is the search engine to connect large amounts of unstructured data to AI. Built from first principles on object storage with an intelligent cache layer, turbopuffer is just as fast as in-memory search engines but orders of magnitude cheaper to run.

We index1T+documents for leading AI companies: