StarZero All shows Try the podcast clipper →

Bill Chen

Applied AI Engineer, OpenAI · 1 appearance on the record.

computed by AI from the episodes · how this works → · full disclaimer →

engineerfounder@realchillben ↗openai.com/index/openai-codex ↗

Bill Chen works on autonomous coding agent architectures and applied evaluations at OpenAI, focusing on harness design and tools like Codex Max. Previously, he co-founded the Y Combinator-backed medical review startup RiskAngle and worked as an engineer at Retool.

7statements → 4claims → 2claims resolved → 3.71/5average certainty → 1.71/5average debate potential →

2 supported 0 partly supported 0 contradicted 2 not checkable as stated how the 4 claims stand · each chip opens the sources

1 prediction · 3 assertions · 3 insights · every statement was checked. The prediction and assertions are the 4 claims: statements the public record can support or contradict. 2 are resolved, and 2 name no date, number or outcome precise enough to check. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Bill argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

Their most notable supported claim

Prediction Held up
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.”
Bill Chen Dec 26, 2025 ▶ 25:40 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI

Expressed certainty vs assessment result

none yet certainty 1
none yet certainty 2
100% certainty 3
100% certainty 4
none yet certainty 5

weighted support: a fully supported claim counts one, a partly supported claim counts half. Each filled bar is clickable and opens exactly those claims; "none yet" means nothing said at that certainty level has resolved yet

Everything Bill Chen said on Latent Space that made the record, most notable first. Filter by type, assessment or year in the ledger →

Insight
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…”
Bill Chen Dec 26, 2025 ▶ 8:05 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
Assertion Not checkable as stated
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.”
Bill Chen Dec 26, 2025 ▶ 8:24 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
Prediction Held up
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.”
Bill Chen Dec 26, 2025 ▶ 25:40 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
Insight
Chen: AI software abstraction is shifting from raw models to packaged agents
“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 b…”
Bill Chen Dec 26, 2025 ▶ 12:28 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
Insight
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.”
Bill Chen Dec 26, 2025 ▶ 24:42 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
Assertion Not checkable as stated
Chen: Approximately 50% of OpenAI employees adopted Codex at launch
“Initially when Codex first launched, it was around 50% of folks that open AI started using it.”
Bill Chen Dec 26, 2025 ▶ 16:28 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
Assertion Supported
Chen: OpenAI's Batch API does not yet support multi-turn requests
“Batch multi-turn requests. I don't believe it. You can't do it yet.”
Bill Chen Dec 26, 2025 ▶ 21:52 ⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI

Appearances (1)

EpisodeDateSpeaking time
⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Che Dec 26, 2025 6m
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more