OpenAI Codex, every mention

mentionsepisodesper episode tap a year for its mentions

Verbatim, from the transcripts: the passages where OpenAI Codex comes up

loading…

▶ 22:58 Vijay Krishnan In fact, if, uh, you know, if anything, if the, um, if the cloud models or codex or even Gemini models or any of these other models, uh, get a lot better at, uh, coding, these people only benefit.

▶ 13:23 Jonathan Siddharth Um, there is a benchmark called Terminal Bench, uh, where you're evaluating, um, Terminal Bench is the kind of benchmark you need for, like, a command line coding agent that has access to a terminal, like, think Cloud Code, Codex, Gemini…
▶ 22:57 Jonathan Siddharth My hunch, um, is that when the models improve in coding, they also improve in tool use, uh, and that helps these generalized computer use agents like Codex, Cloud Code, Geminis, CLI, et cetera.
▶ 37:48 Jonathan Siddharth Uh, use Codex or Cowork or Gemini or Grog to build it. 2 times in the scene

▶ 2:31 Animesh Koratana And there was a variant of GPT-II that, uh, that was called Codex. 2 times in the scene

▶ 21:29 Siddhartha Ahluwalia Claude versus Cursor and Codex and Copilot. 2 times in the scene

▶ 31:22 Sudheesh Nair And Codex is now trying to get better at that. 2 times in the scene

▶ 40:42 Rohit Agarwal Everybody's still saying that Codex is a better model for code generation today, but people still use Claude to think, brainstorm, plan, and then once the plan is ready, it's like, okay, now Codex implemented. 3 times in the scene

Turn any episode into a week of clips.