Josh McGrath

speaker

251 appearances 1 recordings 1 series first heard Dec 2025 last heard 31 Dec

Josh McGrath’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 1 in all, peaking in Dec 2025 with 1.

Appearances

newest first · ▶ plays the moment

Latent Space: The AI Engineer Podcast · [State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI · 31 Dec 2025 podcast

Uh right,

Yeah, yeah.

So now we we have those toggles.

What's your favorite toggle?

Uh honestly custom instruction for like I want I personally want my model to like be a tool.

And so like I don't I don't necessarily like want the the warmth or anything.

I just want some answers because I'm you know, I'm mostly using it at work.

also come down on the side of like using it, using it.

Anton.

Yeah.

Well, I think like we're we're doing a lot of work to provide both like people Antons and Clippies and I I hope they all like it.

Yeah.

I mean, so not necessarily debates internal, but like my read personally from like looking at different papers that are coming out, when you look at like an RL VR paper or like a RLHF paper, they read more like an optimization paper.

And to me, like the the sort of interesting thing that's going on is we have this like spectrum of how high quality a signal is.

So like really at the end of the day, like RLHF, RLVR.

They're both policy gradient methods, but the what's different is just like the input data.

And it's always interesting to me that we call RLHF non-verifiable, because we've trained this model to be good at like predicting human feedback.

So in some sense, that's like verification.

Yeah, yeah.

But like if the if like your value of truth is like does the user like this more?

Showing 81–100 of 251 · page 5 of 13