Chen: AI software abstraction is shifting from raw models to packaged agents
Bill Chen · ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI · Dec 26, 2025 · at 12:28
Bill Chen is an OpenAI engineer on the Codex and GPT-5 training teams discussing agent architecture at the AI Engineer Conference.
0:00 / 0:17exact quote · 17.6s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“So we're actually shipping this Entirety, entire agent altogether, then you can actually build on top of that agent. That's one of the patterns that we're seeing here is rather than focusing on optimizing with every single model release, you're actually just be able to plug in an agent like Codex into your platform and be able to use an app box.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Bill Chen
Chen: Naming custom tools identically to terminal tools boosts Codex performance
“We found some, like, partners of ours, like, they discovered that what you can do is that you can actually still have a lot of the tools just named in the same way as the terminal tools, as well as having the same input and output. And all of a sudden, the too…”
Chen: Codex performs better when search tools are named 'rg' over 'grep'
“So if you call it grep, it actually does a little bit Worse. But if you call it RG, it actually does really well.”
Chen: AI agents will master GUI-based computer use by 2026
“And I can continue just by sort of like saying that that's definitely going to be something I think is going to be something that we'll be capable of in 20, 26.”
Chen: Terminal coding agents are actually general-purpose computer-use agents
“So what would you think about it is are those coding agents are actually a computer use agent, but for the terminal. They're actually incredibly general.”