High Signal Podcasts Evidence ledger
Method
Browse
← All source episodes

Latent Space / episode intelligence

Extreme Harness Engineering for Token Billionaires: 1M LOC, 1B toks/day, 0% human code, 0% human review — Ryan Lopopolo, OpenAI Frontier & Symphony

7 Apr 2026 35 published claims 2 attributable people

Speakers in the public record

Claim mix

belief 15evaluation 6uncertainty 5observation 3commitment 3prediction 2preference 1

Evidence policy

Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.

Claim ledger

The useful parts, with receipts.

35 published records

01 / observation

This has been my experience with platform teams in the past, where you have an envelope of acceptable build times and you let it go up to breach and then you spend two, three weeks to bring it back down to the lower end of the average low bed stop.

“This has been my experience with platform teams in the past, where you have an envelope of acceptable build times and you let it go up to breach and then you spend two, three weeks to bring it back down to the lower end of the average low bed stop.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

02 / uncertainty

I’m also calling back to there’s this like levels of EGI I don’t know if Opening Eye is still talking about this, but they used to talk about five levels of EGI and one of it was like, oh, it’s like an intern coding software patient.

“I’m also calling back to there’s this like levels of EGI I don’t know if Opening Eye is still talking about this, but they used to talk about five levels of EGI and one of it was like, oh, it’s like an intern coding software patient.”
Speaker
Shawn Wang
Publisher
Latent Space

03 / observation

In the same way, you would have a full stack engineer be able to drive a feature from the backend all the way to the front end.

“In the same way, you would have a full stack engineer be able to drive a feature from the backend all the way to the front end.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

04 / commitment

I’m not gonna open up a id, I’m not gonna do anything. But I will say, okay, fix this little thing, change a line, change a color.

“I’m not gonna open up a id, I’m not gonna do anything. But I will say, okay, fix this little thing, change a line, change a color.”
Speaker
Not verified from transcript
Publisher
Latent Space

05 / belief

I think like the only argument I have against this is basically scale testing, which obviously the larger pieces of software like Linux, MySQL, he calls up even the Datadog and Temporals and then maybe security testing where Yes.

“I think like the only argument I have against this is basically scale testing, which obviously the larger pieces of software like Linux, MySQL, he calls up even the Datadog and Temporals and then maybe security testing where Yes.”
Speaker
Shawn Wang
Publisher
Latent Space

07 / belief

The structure of the repository is like 500 NPM packages. It’s like architecture to the excess for what you would consider, I think normal for a seven person team.

“The structure of the repository is like 500 NPM packages. It’s like architecture to the excess for what you would consider, I think normal for a seven person team.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

09 / uncertainty

We were up in the five to 10 PRS per day per engineer. And I don’t know about y’all, but like it’s very taxing to constantly be switching like that.

“We were up in the five to 10 PRS per day per engineer. And I don’t know about y’all, but like it’s very taxing to constantly be switching like that.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

11 / belief

I think we’re excited to do We’re gonna talk about Symphony in a little bit, but like the way we distribute it as a spec, which I think folks are calling Ghost Libraries on Twitter.

“I think we’re excited to do We’re gonna talk about Symphony in a little bit, but like the way we distribute it as a spec, which I think folks are calling Ghost Libraries on Twitter.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

12 / belief

I think your intuition is right, that it’s very great for spiking out prototypes, exploring ideas quickly, doing those documentation updates.

“I think your intuition is right, that it’s very great for spiking out prototypes, exploring ideas quickly, doing those documentation updates.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

13 / belief

All the coding review agent, it can merge autonomously. I think that’s something that a lot of people aren’t comfortable with.

“All the coding review agent, it can merge autonomously. I think that’s something that a lot of people aren’t comfortable with.”
Speaker
Shawn Wang
Publisher
Latent Space

14 / uncertainty

I was briefly part of the, that, that world is it salt? I don’t know. It’s actually really hard for humans to agree on what revenue is.

“I was briefly part of the, that, that world is it salt? I don’t know. It’s actually really hard for humans to agree on what revenue is.”
Speaker
Shawn Wang
Publisher
Latent Space

15 / belief

I had to go do a crash course in Beam and Elixir, and I think most people are not operating at that scale of concurrency where you need that.

“I had to go do a crash course in Beam and Elixir, and I think most people are not operating at that scale of concurrency where you need that.”
Speaker
Shawn Wang
Publisher
Latent Space

16 / prediction

We expect that there will be some harness things there. Agents, SDK is a core [00:59:00] part of this to enable both startup builders as well as enterprise builders to have a works by default harness that is able to use all the best features of our models from the Shell tool down to the Codex Harness with file attachments and containers and all these other things that we know go into building highly reliable, complex agents.

“We expect that there will be some harness things there. Agents, SDK is a core [00:59:00] part of this to enable both startup builders as well as enterprise builders to have a works by default harness that is able to use all the best features of our models from the Shell tool down to the Codex Harness with file attachments and containers and all these other things that we know go into building highly reliable, complex agents.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

18 / belief

I think obviously you can spend the whole day going through some of these, but I do think that some of these have a lot of care or some of this you might wanna tell people, Hey, take this, but, make it your own.

“I think obviously you can spend the whole day going through some of these, but I do think that some of these have a lot of care or some of this you might wanna tell people, Hey, take this, but, make it your own.”
Speaker
Shawn Wang
Publisher
Latent Space

22 / belief

Coming back to the final point I wanted to make is, yeah I think that there, there are multiple other, like you guys are working on this, but this is a pattern that every other company out there should adopt.

“Coming back to the final point I wanted to make is, yeah I think that there, there are multiple other, like you guys are working on this, but this is a pattern that every other company out there should adopt.”
Speaker
Shawn Wang
Publisher
Latent Space

24 / belief

I think one of the concerns I have with that kind of stuff is you think you’re making the right call by making, it’s persisted for all time across everything.

“I think one of the concerns I have with that kind of stuff is you think you’re making the right call by making, it’s persisted for all time across everything.”
Speaker
Shawn Wang
Publisher
Latent Space

26 / belief

Super excitedly part of the Bellevue Community building the future in Washington. And I would say that there is lots of work to be done in order to successfully serve enterprise customers here in Frontier.

“Super excitedly part of the Bellevue Community building the future in Washington. And I would say that there is lots of work to be done in order to successfully serve enterprise customers here in Frontier.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

27 / evaluation

It’s almost like you’re, it’s like a ratchet. It’s like you’re forcing build time discipline, because if you don’t, it’ll just grow and grow.

“It’s almost like you’re, it’s like a ratchet. It’s like you’re forcing build time discipline, because if you don’t, it’ll just grow and grow.”
Speaker
Shawn Wang
Publisher
Latent Space

28 / evaluation

For us as users, it has again, pushed the productivity five x, which means I think there’s something here that’s like a durable pattern around removing the human from the loop and figuring out ways to trust the output.

“For us as users, it has again, pushed the productivity five x, which means I think there’s something here that’s like a durable pattern around removing the human from the loop and figuring out ways to trust the output.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

29 / observation

Which means that often over the agent trajectory, I realize the bits that we’re missing, which is why I find I need to have this synchronous interaction.

“Which means that often over the agent trajectory, I realize the bits that we’re missing, which is why I find I need to have this synchronous interaction.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

30 / evaluation

The tech jet tracker and the quality score are pretty interesting because this is basically a tiny little scaffold, like a markdown table, which is a hook for Codex to review all the business logic that we have defined in the app, assess how it matches all these documented guardrails and propose follow up work for itself.

“The tech jet tracker and the quality score are pretty interesting because this is basically a tiny little scaffold, like a markdown table, which is a hook for Codex to review all the business logic that we have defined in the app, assess how it matches all these documented guardrails and propose follow up work for itself.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

31 / evaluation

Yeah, and I think success for the way we are [01:08:00] operating here means the model gets better taste because we can point the way there and none of the things we have built actively degrade Asian performance.

“Yeah, and I think success for the way we are [01:08:00] operating here means the model gets better taste because we can point the way there and none of the things we have built actively degrade Asian performance.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

32 / preference

If you think that code is context, code is prompts, it’s better from the agent behavior perspective to be able to look in a package in directory X, Y, Z, and it not to have to page so [00:40:00] deeply into directory if you C, because they have the same structure, use the same language, they have the same patterns internally.

“If you think that code is context, code is prompts, it’s better from the agent behavior perspective to be able to look in a package in directory X, Y, Z, and it not to have to page so [00:40:00] deeply into directory if you C, because they have the same structure, use the same language, they have the same patterns internally.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

33 / prediction

We want AI to be deployed widely, to do economically valuable work, then we need to find ways for them to naturally collaborate with humans, which means collaboration tooling, I think, is an interesting space to explore.

“We want AI to be deployed widely, to do economically valuable work, then we need to find ways for them to naturally collaborate with humans, which means collaboration tooling, I think, is an interesting space to explore.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

34 / evaluation

10 times slower than I would be. But because we paid that cost, we ended up getting to something much more productive than any one engineer could be because we built the tools, the assembly station for the agent to do the whole thing.

“10 times slower than I would be. But because we paid that cost, we ended up getting to something much more productive than any one engineer could be because we built the tools, the assembly station for the agent to do the whole thing.”
Speaker
Ryan Lopopolo
Publisher
Latent Space

35 / evaluation

Fundamentally, software is made more flexible when it’s able to adapt to the environment in which it is deployed, which means that things like linear or GitHub even are specified within the spec, but not required pieces of it.

“Fundamentally, software is made more flexible when it’s able to adapt to the environment in which it is deployed, which means that things like linear or GitHub even are specified within the spec, but not required pieces of it.”
Speaker
Ryan Lopopolo
Publisher
Latent Space
Search evidence