A (2:42)

And see which model performs best.

B (2:46)

Yeah, we're now both. They're going to do a head to head to try to each build their own version of polymarket.

A (2:51)

So by the end of this episode, you will have a pretty good understanding of how to use the models, when to use the models, how to get started. Morgan, let's get into it.

B (3:01)

Cool. Right on. All right, so I took some notes and essentially, you know, with 5.3 codecs, I'll be showing that in the desktop app on Mac because they're super excited about that. I'm excited about it. I think if OpenAI was wanting a demo to be done the right way, they would want me to do it in their app. Whereas with Opus 4.6, I would say the Anthropic team would want me to do it in the cli. And so there's a few different configuration settings that you do want to make sure that you get right when you're using Opus 4.6 or trying to use Opus 4.6 today, tomorrow, whenever it is that you're jumping in to use it. I've seen a lot of people online today on Twitter saying it's weird, I'm having a problem, like it's supposed to be agent teams, but I don't see them or how do I know what version I'm running? So I thought, let's start by just giving everybody a level playing field to know, okay, I want to be able to use Claude code with Opus 4.6. How do I make sure I'm doing that and doing that correctly? So here's kind of the initial to dos that everyone should have on their list. Just do an NPM update, see if that does the trick. If that doesn't and you're running an older version, then run Claude update. But you should see, like as of right now, it's 2.1.32. If you see 1 dot something, you're running an old version and then what you want to do is go into your settings JSON and I'll just show this here. So if you just do like CD tilde slash claude.

A (4:37)

So I bet that there's people who are running the old model, they don't even realize it. Bad results.

B (4:45)

Yeah, yeah. So I mean, make sure you go in here CD total CLAUDE here's your settings JSON. If you view this, here's essentially what you should see. Now, it's okay. It can be model. If you want to like really be specific about it, you can put in Claude opish 4. 6. That'll lock it in. But because 4.6 is the newest model, you can also just put in model and just opus, and that'll work. The key thing that you want to do is, in my opinion, the coolest feature that they added with four. Six is agent teams. I'm super excited to demo that with you. You have to make sure to turn that on because it is an experimental fe. And that's probably the biggest confusion I'm seeing people have today with Opus 4.6 is that they are running Opus 4.6. They keep hearing about agent teams and they're giving it prompts like build a team of agents, do this and this, and it's not quite doing it. And that's because you do have to enable this. So you do have to add in ENV this Claude code experimental agent teams, and then set it equal to one. Okay, Nothing too crazy. Once you do that, that will make all that possible. So with that in mind, you're pretty ready to go there. Then you can just run CLAUDE in the terminal and you're good. For people that are using the API. The one thing I did want to point out is there's a pretty cool new addition, which is called adaptive thinking. Also, just to be clear, because I'm seeing confusion on this too. This is in the API, this is not in Claude code itself, but adaptive thinking. Just to show it, here you're able to essentially pick the level of effort that you would like the model to use. This is only going to work in 4.6, by the way, if you want to use like an effort level of max. And so here's kind of the different levels. So with Max, Claude always thinks with no constraints on thinking depth. It's Opus 4.6 only. So requests using MAX on other models are going to return an error. So if you're calling the API and you set the effort level to max and you get an error, then you're probably not using Opus 4.6. But here's the example where you can see if I'm calling the API, I set the model to Claude Opus 4.6, and then here's where I can set the effort. And this is another thing. If you're using existing API code, you may have the model of Opus 4.5 and now you adjust the Effort to max it gives you an error. All you need to do is just bump the version and you're good. But this is kind of a neat thing they've added to The API with 4.6, it's worth mentioning. And then kind of the last, the last thing I would say is just if you want to use split panes for agents. So if you want agents to show up in different panes and you're using something like Warp, just make sure to install tmux. You can do this with Brunt. And then if you do that, it's going to default to auto, which usually means in process, which means in that same terminal window you have, the agents are going to be working all together. If you want it to split pane, then you just need to update that setting in the settings JSON to split panes. I'm not going to go into super details on that, but those are just like, I think good housekeeping to start with for anyone using Opus. But don't worry about it really, all that anybody needs to do, especially if you don't even want to use teams, agent teams, is just make sure you're updated using the newest version and that the model is Opus and you'll be using Opus 4.6.

A (8:21)

Cool.

B (8:22)

So that's that. Before I get into kind of the differences between Opus 4.6 and Codex, I thought I would actually read this because this was posted on Hacker News four hours ago. And I was reading it, I was thinking that's like the best way to explain it. So I'm just gonna. I'm just gonna read this little section here. Cause I think they do such a good job with it. This person's saying. What's interesting to me is that GPT5.3 and Opus4.6 are diverging philosophically and really in the same way that actual engineers and orgs have diverged philosophically. I think this really nails it with Codex 5. 3. The framing is an interactive collaborator. You steer it mid execution, stay in the loop course correct as it works. With Opus 4.6, the emphasis is the opposite. A more autonomous, agentic, thoughtful system that plans deeply, runs longer and asks less of the human. That feels like a reflection of a real split in how people think LLM based coding should work. Some want tight human and loop control. Others want to delegate whole chunks of work and review the result. And I honestly, I think that says it beautifully and I think that that nails the differences. And also hopefully, you know, there's all everybody wants to pick a winner where it's like, oh no, no, opus 4. Six is better. Codex is. It's, it's different. It depends on what your methodology is. And I think what we're seeing now not just with Vibe coding, but also with like overall like AI powered engineering is how, how do you want to work with agentic coding? Do you want to have a totally autonomous experience where you're sending agents out to do work or do you want to work with an LLM, like another teammate and pair program with the LLM? And, and that's where you're now seeing a divergence where I think you're going to see a lot of teams using both because Codex really is your collaborator. And what they've added with 53 is like really good, like mid execution steering. Whereas with, with Opus 4. 6 it's probably the best of the best now being able to say I want to spin up three or four agents, I want them to go do stuff. Hey, don't bug me. I want to trust they're going to do good stuff. Um, and it's able to deliver.

A (10:38)

So are you saying that there in some ways it's just a preference, like depending on how you know there's no right or wrong. Basically, you know, you're not wrong to be an Opus person or you know, it just like might feel. Yeah, it's just a preference.

B (10:56)

Yeah. Well, and you might be both.

A (10:58)

Right, that's true.

B (10:59)

It might turn out that you're both. That's why like not to disappoint people here. But we're not going to end this with me saying and so the winner is. It's like well depend. Depends on what you want to do. Everyone has a different methodology for it. So I'll dive in and try to try to make this part fast because I know the fun part is probably us going in and playing around with both of these and having them do a head to head and try to build a competitor to Polymarket and however much time we have. But I'll just start kind of going into these at a high level just so for anyone wants to know like what are the core differences? Why is this so interesting? Just kind of what that is. So with, with Opus 4.6, much bigger context window. So you have a million token context window here. Very strong coherence over entire documents and repos designed for, you know like load the whole universe and reason over it. 5.3 they talk about large context but it's not a headline feature. And I actually went back and forth with it to get it to actually give Me a number and the numbers 200,000 tokens which is not that impressive. That's smaller than I was thinking it would be. But that's okay. It's optimized for progressive execution rather than total recall. So that's why that's not as important. And optimized for deciding what to keep in working memory. So high level. What that means is Claude is better when the task is understand everything first and then decide GPT 5.3 codecs is probably better when the task is decide fast act iterate more of that pair programming mid task change behavior. For coding benchmarks. Opus 4.6 is really good at code based comprehension Refactors with architectural sensitivity. Explaining why a system behaves a certain way and then you know, a little less tendency of this like YOLO write code. Right. Which is I think something everybody wants.

A (13:06)

Yeah, exactly.

B (13:07)

So you know, that's good for everybody. But especially for vibe coders that are getting started and they may not be able to identify hallucinations. Opus 4.6 is definitely going to perform better there. But then for teams, you know, building in large code bases like like me and my team are doing, that's also really important. So kind of a win for everyone there. 5.5.3 Codex did win on SWD Bench Pro Terminal Bench. Overall it's like scored better on coding benchmarks. So probably better end to end app generation. And you know Claude's kind of like senior Reviewer Staff Engineer GPT 5.3 probably like your, your founding engineer, right? Agentic Behavior Opus4.6 this is the key one right is like the multi agent orch that's, that's probably like the bleeding Edge feature in 4.6. And then with, with, with 5.3 Codex really like task driven autonomy build test modify without being asked. But then this task steering, you can watch it, you can go in. It's like your buddy's coding and you can say oh wait, wait man, wait, why are you doing this? And you can stop it and it'll go okay and then you can restart. You can really fix things in line with. Much harder to do that with. With Opus. With Opus you'll kind of be stopping it and then starting somewhat fresh. But it has a pretty big context window so. So it knows what it did. But you know, Claude's really asking like should we do this GPT GPT5.3 is like how fast can I ship this right?

A (14:40)

It's really, I mean it's so cool because it almost feels like they're different people, you know what I mean? Like they have different styles.

B (14:48)

Yes, totally. Yeah. It's a good way to look at it. It's like a different personality type. Right. And then, yeah, failure modes, you know, Claude 46, it might overanalyze. It's got a much bigger context window. It can hesitate when requirements are ambiguous and then it can stop short of full execution. 5.3 codecs could be overconfident, can lock in a flawed assumption early, but you can steer back in the right direction if that. If that happens. So that's kind of a high level overview on the, on the two.

A (15:25)

Cool. That's helpful.

B (15:27)

Yeah. So should we, should we just dive in? I haven't tested any of this. So this is. Now I have like zero can demos because I thought it'd be more fun just to try something together and see what happens. So should we, should we try it?

A (15:41)

Yeah.

B (15:41)

Okay. So let's see. I'm going to. I'm going to start with Opus, and I've got these prompts preloaded, so I'm giving different prompts. Just like I think you said it really well. It's like you're talking to different people. And so, you know, when I'm talking to Opus, I can tell Opus, build me a team. And here's what I want each member of the team to do. When I'm talking to Codex, I can't really tell it to build me a team, but I can tell it to think about stuff. So the prompt that I'm going to give to Opus is build a competitor to polymarket. Create an agent team to explore this from different angles. One teammate on technical architecture, one on understanding polymarket and the ins and outs of prediction markets. One on UX and one that just works on building really good tests to make sure everything works. For Codex, I'm going to give it a little different prompt, but very similar. So I'll still build a competitive Polymarket, but now think deeply about technical architecture, understanding polymarket and the ins and outs of prediction markets. Good, clean ux. Make sure it builds really good tests to make sure everything works. And to be fair, I'm going to try to paste these in around the same time.

A (16:52)

You're a fair guy, Morgan.

B (16:54)

I'm trying to, I'm trying to keep it fair here. Right. That's the only way to do it. Like I said, no. No winners or losers.

A (16:59)

It's.

B (17:00)

It's just about, just about letting everybody have a fair shot to play the game.

A (17:05)

Yeah.

B (17:06)

All right, so let's see. I'm going to make different directories so I'll do. Let's just call this Opus4.5 polymarket competitor. All right, so let's fire up cloud in here. By the way, if you want to check when you're running, just to, like, really make sure that you're in a good place with the model. If you type slash, model, I can see here, right? Claude, Opus 4. 6. Right. So I'm good there. I'm going to take this prompt, copy it, make sure this is all copied incorrectly. Okay, Got that. I'm not going to hit enter yet. I'm making this totally fair. I don't want anyone at Anthropic or OpenAI to get upset with me. So I want to be in good terms with both of them.

A (17:55)

Totally smart guy.

B (17:57)

Let's see. Oh, wait. Actually, you know what? I do want to create a new.

A (18:00)

Folder for this, but we are keeping it real. We're being objective. Neither myself or Morgan are affiliated with either. Well, actually, I don't know about you. I'm not affiliated.

B (18:10)

I'm not.

A (18:11)

I'm not.

B (18:11)

I'm not. Nope, Nope. I love them both equally. How about that?

A (18:17)

Yeah.

B (18:18)

Okay. And I'm going to try to start them as close to on the same time as I can. Enter. Go. All right. They're going off to the races.

A (18:30)

So what do you think's going to happen?

B (18:33)

That's a great question. Well, I know right now because I told Opus 4.5 to build using different teammates. It's going to do that. So you can see here, it says, I'll build a polymark competitor by launching parallel research agents first, then synthesizing their finding to a comprehensive implementation planning code base. This is brand, brand new, right? Like, if I did this with OPUS yesterday wouldn't be possible. That's kind of the difference here, is that the way that Codex is working is the way things have kind of always worked, right? So if you see, this is like the individual visual person, right? It's not saying, okay, I'm going to launch all these different agents and compare what they say and say, okay, I'm going to inspect the workspace. This is your, you know, really detail oriented, really senior, like, founding engineer, like that example gave.

A (19:28)

Right.

B (19:29)

Whereas over here, you can see it's already launched these agents and now it wants to do web searches, and I'm going to let it do that. So multiple agents were asking to do web searches, so now. Now launching all four research agents in parallel. So this is off. And I've got, you know, my technical architecture agent. I've got this other agent that these are both doing web searches right now. So one is looking at like prediction market order book matching engine architecture. So this one's learning about engine architecture for prediction markets. This one' looking at polymarket, how it works, bar predictor, market mechanics. And then I've got the UX design is doing some design research and then we've got some test research. Okay. Now it's going to go to Polymarket and let's really hope the polymarket doesn't block it because that'll make things harder for it. Meanwhile, over here, this has discovered Coax has figured out the repo is empty. So it's going to scaffold it from scratch. And it is starting to. I'm now wiring the core market math and trading engine. So it's interesting. Right, so you've got Codex is out here building and is like building the engine. With Opus 4. 6. It still has agents out there like doing research work.

A (20:48)

You really start to see just like how different they really are as they make progress.

B (20:55)

Yeah. Like I said, I haven't tested it before so we don't know how long it'll take each of these.

A (21:00)

Totally. Yeah. And I think like, I guess one question I have is like, is 1. Is one model better for being more of a beginner, non technical vibe coder or you know, does it really matter?

B (21:16)

Yeah, it's a good question. I mean, I think the fair answer would be probably Codex because Codex edged out Opus4.6 a little bit on some of those coding benchmarks and is kind of known for writing better production code, probably Codex in that way. At the same time, one of the downsides, and like I said this is I could only do this in a totally balanced way because they're so different, you know, at the same time. For a Vibe coder, knowing when to interject and stop codecs and say, oh wait, you're doing this this way. Can you instead look at doing it this way? They're probably not going to know how to do that. Right. And so that's where maybe Opus 4. 6 is better. Where you could say, okay, spin up four or five agents and let them work with each other. Right.

A (22:11)

Yeah.

B (22:13)

Okay, Codex is done. All right, so Codex built a competitor to Polymarket in 3 minutes and 47 seconds.

A (22:22)

And to be clear, Polymarket's a multi billion dollar company.

B (22:25)

Yeah, I don't think this will work quite as well, but we'll see. Let's see. So let's just check out if it worked first. I'll let this keep Running here. So, you know, it'll tell you at the end here it actually did the testing. So you can see it built a test suite. So it has an LMSR math unit test suite, an engine behavior unit test suite, and an API integration test suite. And it passed with 10 out of 10 tests as far as what it built. It has this core LMSR market maker engine. So coherent pricing, slippage bound loss behavior, domain trending engine. It built a REST API router, which is kind of interesting because I didn't tell it that it would have to build obviously, any of this in any way. It figured out the architecture on its own. Clean, responsive front end. All right, well, let's see. Let's see if it is actually. So let's go here. I'll let this keep running. This has got these four agents just running away here and I'm in here. I'm going to do npm test. All right, tests. 10 past 10. That looks good to me. Npm start. All right, it's running. Let's see. Okay, here we go. So this looks like it has the ability. So let's. Greg, let's make you. We'll make you the first trader. All right, Say add. Okay. You got a thousand bucks.

A (24:05)

Okay.

B (24:05)

There we go. Not bad. All right, what. What market do you want to create?

A (24:12)

Well, Bitcoin, I think, as we speak, has crashed to what, 63,000 or something?

B (24:17)

Something like that. Yeah.

A (24:19)

So I do like the. I mean, will BDC be about, you know, be above 110k by.

B (24:25)

Yeah, okay.

A (24:28)

By des 31.

B (24:29)

20.

A (24:29)

20.

B (24:30)

Pretty good. Yeah. Okay.

A (24:32)

I mean, that's almost double.

B (24:34)

Yeah, that'd be pretty good.

A (24:38)

It depends. Depends when you bought it. You know, if you bought it at 125k, then, yeah, you're not so happy. But let's see.

B (24:47)

So then I don't know. I don't even know what resolution criterion, source, what is be. I mean, I think I know what it's getting at, but I guess you could say, like, why don't we say, use Coin market cap as the source and resolve by looking at the price on the last day of December, just before midnight, I guess.

A (25:16)

Yeah, I guess. Like.

B (25:20)

The price of btc.

A (25:23)

Yeah.

B (25:23)

All right. Okay. It looks like it's okay. So we've got it now. So we'll use CoinMarketCap. Okay. So then you could do a yes, 50%. So what do you think? Yes. Yes or no?

A (25:39)

I mean, this isn't financial advice. This is just purely educational purposes. But I think. I think so. I think that.

B (25:47)

All right, that's a yes for Greg. Buy. Let's see how many shares you want to buy. You've got a thousand bucks.

A (25:56)

I want to put it all, I'll put it all on this.

B (25:59)

I don't know how much it is per share. Let's see if it's a thousand if that's right. Okay. Yeah. Okay. Trade executed. Okay, so I mean it seems like it built something as a prototype, relatively functional here. I, I guess that it actually has decremented. So, okay, a thousand shares was not. That ended up being, you know, about $24 that you spent. So you've got more money if you wanted to create another market. But it worked. It's not returning an error. It shows the volume here. Interesting. All right, so let's go back, let's see. So far so good with that. I'd say let's see what's going on here. So we've got. Okay, so first off, look at how many tokens. People have been talking about how token hungry OPUS is and it's very token hungry. Each one of these agents has used over 25,000 tokens. So let's see though. So they finished, Right. The technical research around architecture is done. Prediction market research is done. The UX design research is done. The testing strategy is done. Now it's going to go and build. So it's writing the package JSON.

A (27:17)

Did you see the ad that Anthropic launched about ads?

B (27:24)

Yes, I watched them all. They're hilarious. Although actually I guess Sam was not very happy about them today I saw a tweet from Sam that was less than happy. So I also, I found them hilarious. But I also understand his side as well.

A (27:40)

It seems like Anthropic is sort of anti ads for now and ChatGPT is going to be introducing ads.

B (27:47)

Yes.

A (27:48)

And you know when I'm watching this and I'm seeing you're going through 25,000 tokens. 25,000 tokens. 25, Thousand tokens. I'm like, yeah, of course Anthropic doesn't.

B (27:58)

Really exactly, you know. Yeah, yeah. I mean this is literally, I mean if you add that all up, you're talking about over a hundred thousand tokens used in doing this. So I think that's one of the very good things for like investors in Anthropic. Right. Is with agents and agents now being, I think probably the new killer feature in opus. You're going to take whatever token usage and multiply it by the number of agents.

A (28:27)

Exactly. It's actually really smart. And I wonder if that was the thinking. They're like, how can we get people to use more tokens? Oh, we'll just spin up agents and we'll design it like that. Or did they think, okay, how can we design a system that is best for the use case? And then they're like, okay, and then we'll monetize it like this?

B (28:47)

I don't know. Yeah, yeah, Probably a combination of the two. I can tell you I've never used so many tokens in one day as today. So it's working.

A (28:57)

100. 100,000 tokens is like roughly how much in US dollars.

B (29:02)

I don't know, because I have a. I have a Claude Max plan. Yeah. So I'm not paying. We're not seeing it hit any limits right now. Right. So I'm not paying more than $200, I can tell you that.

A (29:16)

Yeah. My guess is it's, you know, we're talking like in the $200 max plan, do you remember how many. How many tokens you get approximately?

B (29:29)

That's a good question.

A (29:31)

Let me check.

B (29:32)

Fire up. Let me fire up Claude and ask it. Let's see here. How many tokens do I get? Estimate. Let's see. Okay, so here you go. Estimate estimates. So 45 million tokens per month of sonnet. But let's see, what is your estimate for opus or six?

A (30:00)

It's like they don't really want you to know.

B (30:02)

No, they're trying to make it a little harder. Okay. Yeah. They're not even going to tell me, actually. They're just going to say there's no public data. It's very new. Opus is roughly 5x more expensive. So then if it's 45 million, that's 5x. So 10 million is probably the answer. About right.

A (30:19)

Yeah.

B (30:19)

Yeah.

A (30:21)

So then if we're doing quick math, let's just say we spent 100,000 tokens. 100,000 divided by 5 million is.

B (30:34)

Well, we're going to spend more than that because look at this, we're now over 17,000 tokens on top of that in this next build. Okay, but still, let's say even if we use a million tokens building a competitor to Polymarker right now, we're still only using a tenth of what it. What it can do. That's not terrible.

A (30:55)

No, I mean, it's $20, which is like the price of a cocktail in Miami.

B (31:00)

Yeah, yeah, exactly. Yeah, yeah. Let's see. But now for. As I say, I'm watching the tokens creep up all Right. So it's building the API routes now.

A (31:15)

I have a feeling this is going to be a better end result.

B (31:18)

I was actually just gonna say that this feels. And maybe it's just because there were four agents that were doing all the work beforehand and now it's doing the work. It feels like we're gonna see something very different when we. When we load what it builds.

A (31:35)

Yeah. I don't think we gave it any, like, design, like, visual design, any, you know, so.

B (31:41)

Nope.

A (31:42)

Do you recommend for folks to just like, sort of get the MVP out, play around with it on localhost, you know, click some buttons and then sort of update with the visual design from there?

B (31:55)

It's a good question. I do like 5050 sometimes if I have something in mind, especially if I want something like on brand with something like suppose I'm building something that is going to be in the, like, open claw multiple ecosystem. I would probably say, hey, I want to design a site that, you know, looks somewhat similar to or is inspired by, you know, open. OpenClaw AI and multbook.com. right. Take a look at those sites and get inspiration. These models are great at doing stuff like that.

A (32:32)

Cool.

B (32:33)

I'm really excited to see what this is doing, though. I think we're now like, well over 200,000 tokens, based on what I could tell. But we're not at 10 million.

A (32:44)

We're not hitting any limits. We don't have to take out second mortgages on our.

B (32:49)

Yeah, there we go. Yet it's still going, though. I guess we can tell. Here's an interesting thing. In a comparison, this is still going. Why don't we say the design. Because I looked kind of bland to me, right?

A (33:06)

Yes, it did.

B (33:12)

Can you spruce it up and make it look nicer? Because, like, we may as well have codex working away too, right?

A (33:19)

Yeah. So you bait. You didn't really give it any, like, specific. It should look like square.com.

B (33:25)

No.

A (33:26)

Let's see. We'll basically see if. If Codex, if, you know, if 5.3 has a little bit of taste.

B (33:35)

Yeah, yeah. So that's what it's saying now. It's saying, okay, I'll upgrade the visual system without changing functionality. Stronger typography, richer color direction, better card hierarchy, and purposeful motion. I don't know what that means, but we'll find out. All right. Okay, so now it's. Now it's editing index HTML. It looks like it's going to add motion hover polish. Okay, totally. That this current task were over 30,000 tokens building the front end UI. Okay, it's done.

A (34:06)

Yeah.

B (34:07)

Codex is fast, by the way, right? I mean, that's pretty darn fast.

A (34:11)

Yeah.

B (34:12)

So we should be able to just go here. Should have already automatically reloaded, but. Okay. All right. I mean, I mean, not that different.

A (34:22)

Not that different. It's. Yeah, I think. Can I try something?

B (34:28)

Yeah, go for it.

A (34:29)

I'm gonna say. I'll. I would say, okay, thank you. But this was a minor design refresh. I'm looking, I'm looking for a major one.

B (34:41)

There you go. Yeah.

A (34:42)

And then I'm gonna say pretend you are Jack Dorsey.

B (34:51)

Here you go.

A (34:52)

And how would. He designed this website to be clean, elegant, full and full of interesting interactions?

B (35:04)

Yeah. Great. Yeah.

A (35:07)

Jack Dorsey. For people who don't know. Co founder of. Formerly known as Twitter and square block. Now he's just got. He's got. He's a design guy. I don't know. He's first one guy came to mind or first person came to mind.

B (35:23)

Yeah, that's a good one. That's a good prompt. Let's see. So I'll do a full visual rearchitect, not an incremental tweak. New layout language, stronger typography, monochrome first palette. Interesting interaction driven cars. Okay. You know what's interesting is it didn't. I would have kind of hoped, and maybe, you know, we're not quite at AGI yet. I would kind of hope that it would say, let me go find some art. Like if you told me that, Greg, like, hey, Morgan, can you read? I would be like, yeah, let me go look at some articles about Jack Dorsey's design aesthetic.

A (36:00)

Exactly.

B (36:02)

I'm surprised it's not doing that. Instead it's going like. I am assuming it knows who Jack Dorsey is. Although I don't know if it actually does. It just seems like it. It's. It's really just taking like this part of your question and going, oh, okay, major refresh. I'll do that.

A (36:18)

Well, can. Can't you ask it? Can't you say, do you know who Jack Dorsey is?

B (36:22)

I can actually. I'm supposed to be able to. In the middle. Cut it off. So let me see. Yeah. Do you know who Jack Dorsey is? Let's see. Okay, so here we go. This is the midstream test. Thinking about it. 43,000 tokens over here. Okay. Yes. Okay, here we go. Yes. Jack Dorsey is the co founder of Twitter, formerly Logan Square. Okay. With a design style that's typically minimal restraint and interaction focused.

A (36:56)

Beautiful. Okay. All right.

B (36:59)

So Touche. It showed us.

A (37:01)

Yeah.

B (37:03)

Now, here's the weird thing. It looks like it's.

A (37:05)

Is it complete or do we have to say complete?

B (37:07)

Like, right when I was saying that, like, are you done or did you stop because I asked a question?

A (37:14)

Yeah, this is really interesting. I will say, like, Oh, I paused when you asked the question. The major redesign mostly, if you want to resume.

B (37:26)

So that's weird. So you ask it a question, it just stops. But, like, so, like, yes, of course. Continue. Yeah. Okay.

A (37:35)

So that's actually some weird ux. Like, it obviously should just continue after.

B (37:39)

Right? Yeah. I would assume that it's such a weird thing because it said, yeah, if you want, I'll resume now.

A (37:47)

I will say. I, I do like that you can, in midstream, like, kind of edit things.

B (37:53)

Yeah.

A (37:53)

Like, that's how my brain works.

B (37:55)

Totally. Yeah. Yeah. Truth is, using a ton of tokens.

A (38:01)

Yeah.

B (38:02)

It is amazing to see the detail. I mean, this, this should be a work of art, whatever site this comes off with. All right, this is done. So now let's see. We can go back to this and. Okay. I mean, I'm not blown away, but it's okay.

A (38:22)

Opinions become price in milliseconds. Trade conviction, not noise. Signal market is done for fast thesis iteration with transparent pricing. Okay. I mean, I, I, I would push it more, I think.

B (38:38)

Yeah. Yeah, I guess. Yeah.

A (38:41)

Like, I would say go for it. I would say that's not the Jack Dorsey I know.

B (38:48)

I don't know Jack Dorsey.

A (38:54)

I was looking for a Caps lock major upgrade. That, that might mean way more copy, way more images.

B (39:08)

Yeah.

A (39:10)

Way more storytelling.

B (39:12)

Yeah, exactly.

A (39:14)

Et cetera, et cetera.

B (39:15)

Yeah. I'll just say, seriously, take your time. Go nuts.

A (39:19)

Yeah.

B (39:20)

What are credits?

A (39:23)

Famous last words, Morgan.

B (39:24)

I know, right? It's like, oh, perfect. Okay. That's like a signal within the opening of headquarters. Like, we finally got someone.

A (39:30)

Totally. It's a whale.

B (39:32)

All right, so Opus has finished.

A (39:35)

Yeah.

B (39:35)

I have no idea how many credits that use, but probably. Actually, let me ask it. How many, how many tokens in total did you use to put all of this together, including the four agents? And then we can. Oh, it's using token stance.

A (39:52)

That's so funny.

B (39:54)

Okay. Doesn't know. Let's see. Okay, here we go. Okay. It's estimating. It actually doesn't know, which is weird because it should do. Although, wonder if I can actually do cost. Oh, here we go. Yeah. Okay. Oh, it doesn't.

A (40:13)

Okay.

B (40:13)

No, no need to monitor cost. Okay. They really don't want you to know. Okay. It's guessing 150, 250,000 tokens total.

A (40:22)

Yeah, that's probably right.

B (40:24)

Okay, sure. Okay, so here's what it's done. So first off, one really interesting thing here is, you know Codex created 10 tests, right? Opus created 96 tests. So definitely a lot, a lot more detail on the testing side. And it's called it Forecast, whereas Codex called it Signal market. So different names. A polymark competitor is built and verified. Here's what each team member delivered. So the architecture, technical lead decided. Modular monolith. Next JS14 app router, central limit order book, database schema, RESTful API. Okay. The prediction market, domain expert, binary yes, no market where yes no is always a dollar. Okay. Seeded markets across crypto politics. Okay. The UX design lead, dark mode trading platform pages. It is a green for yes, red for no. Okay. Testing. QA lead did order book tests. Okay. So here's how the tests are breaking out. Order book tests, matching engine. Okay. All right. NPM run dub to start the app. So let's go in here. Oh, interesting. Okay, I don't want to say anything, actually. I've already given to it. What's your initial take?

A (41:49)

I mean, my. Hello, Jack Dorsey. You know what I'm saying?

B (41:54)

This is.

A (41:55)

This is what I expected it to look like when we pushed Codex.

B (42:00)

Yeah, me too.

A (42:02)

This looks really clean. What happens when you hover over?

B (42:07)

Oh, yeah, look at that.

A (42:09)

Yeah.

B (42:10)

Hover states. Hover states. Yeah. It's obviously got it organized like sports, you know, Will. The next tube will have over 120 million viewers. Will AI pass the Turing Test by 2027? Will a movie. It's got stuff in there. Yeah.

A (42:26)

Yeah. It doesn't feel like an mvp.

B (42:30)

Yeah, this is pretty wild actually. And it created some stuff, you know, that we never talk to it about. Right. Like a leaderboard, which it's already populated with some initial stuff. Portfolio, section. Yeah. Interesting. So let's see now. So, I mean, I'm more impressed with the. It was maybe worth the 150,000. 50,000 tokens. Feeling better about it? Will SpaceX land humans on Mars before 2030? Only 8%, it thinks. Huh. Oh, yeah, look at this, actually. Whoa.

A (43:05)

This is insane, bro.

B (43:06)

That's clean. Yeah. I wasn't expecting to click in and actually get a well designed a page like this. Huh. So if I were to do that, I have to sign in a trade. I don't know if I'm going to be able to sign in because I haven't set anything up. Let me Just check.

A (43:21)

Well, you can sign up. Says, don't have an account.

B (43:25)

Oh, yeah, sign up. I don't know if it gets it all connected, though. Let's see, though. All right, I'm snagging. You know what, actually, I'm going to take the username. Greg, steal your username. All right, let's see. Okay. So, yeah, it's probably because I was going to say the database isn't wired up yet.

A (43:43)

Right.

B (43:43)

So I'm not surprised that I would actually have to do. I wasn't expecting to do that, so. But I get it. I mean, it's clean. This is pretty neat.

A (43:52)

Yep.

B (43:53)

Yeah. All right, let's see. So then can this. All right, we've given. I don't know about you, but this is the last chance I'm going to give Codex. On the design side, it's out of opportunities here, so. Oh, here. It's funny, though. In the end, it kind of. It's acting a little bit like data from Star Trek. On your question, what are credits in this context? Credits usually means wasn't quite it. That's good, though. Okay, so let's see. Let's take a look and see. All right, here we go. The new version of Signal Market.

A (44:26)

Boom.

B (44:27)

Oh, okay, this is getting a little bit interesting. Let's see here. Read the manifesto.

A (44:36)

Yeah. I mean, I don't hate it.

B (44:39)

It's definitely better. Yeah.

A (44:42)

I mean, it's. It's got a lot going on.

B (44:46)

Yeah.

A (44:47)

But it's different terminal. It's different than. Yeah. Different than any sort of prediction market app I've seen from a UX perspective. I just feel like this is just so clean, though.

B (45:03)

This is so good. It's so fast. Yeah, yeah. I mean, I would say, you know, like I said, I'm not going to say which one is. It's not that Opus is better than Codex or vice versa, but I would say in this test, Opus One.

A (45:16)

Yeah. In this test, Opus One.

B (45:18)

Yeah.

A (45:19)

That's just the truth.

B (45:21)

Yeah. Yeah. But we could give it another. I mean, you know, you never know. Like, I think that what's interesting about this is, I mean, Codex built it, like, I don't know how much faster we can look at the timing on this video, but like 20 times faster or something, right?

A (45:37)

Yeah, yeah, yeah. Well, anything else you want to cover? I don't think we'll have time to do another example, but anything else you want to cover between, you know, that you want to leave people with?

B (45:50)

Yeah. Let me see if there is anything else in here. I cover the adaptive thinking. Oh, I guess just on the orchestration I would say, you know, this is the feature I'm probably the most excited about with Opus and clearly we saw in this example it working really well. Just make sure to look at the documentation. It's all in the docs now and it gives some examples as well because it has this idea of like compare with sub agents of like context and communication and coordination and kind of breaks this down and then it has like a sample prompt, more of the details on the display mode. There's a lot of other stuff that I didn't go into there. That's probably what I would leave people with because I think a lot of people are going to want to dive in and use use agents with Opus4.6 and they've got pretty good details on all little tweaks that you can make with it.

A (46:45)

Amazing. Well, Morgan, I can't thank you enough for coming on. I hope people love this episode. I love talking to you. You get.

B (46:54)

So thank you for having me, Greg. It's a total honor. You're.

A (46:59)

Yeah, it's just I love how clearly you communicate and to technical people, but also non technical people and you're criminally underfollowed. So I'm going to include.

B (47:10)

I appreciate that.

A (47:11)

Links where you can find Morgan and follow him on X. He talks a lot about vibe coding over there. And Morgan, any. Anything else you want to. You know, places that you want to leave people to go and check you out?

B (47:25)

Yeah, I mean I'm the co founder and CTO of Bold Metrics. I'll just give a little plug for us. We have a AI technology that's used by apparel brands and retailers. So if you're shopping online and want to find the right size, you see a find my size button. We a lot of times power that and have really powerful machine learning models that update and adapt over time to help people find the right size and give of really interesting data to lots of amazing brands and retailers that you probably all know and love. And me and my team, you know, we're using all of this tooling. Like I had a meeting with my team this morning about Opus 4.6 and Codex and I've given everybody access to both of these and I actually have multiple teams of mine that are trying current things we're working on and are actually testing with each to see which performs better. So you know, the one thing I encourage all engineering teams to do is like. And engineering leaders to do is like let your teams loose with this stuff. Let them try it. You know, some of this stuff is really cutting edge and really performing and gives us the opportunity to do better, more creative work.

A (48:34)

Yeah, stop listening to us right now. Like, yeah, exactly. Stop listening x out of this YouTube or Spotify link, but actually give us a like a comment and subscribe. Let us know if you like this episode. But Morgan, thanks again for coming on the show. This was a lot of fun. See you next.

B (48:52)

Thank you so much. Total honor.