# Opus 4.6 vs GPT 5.3: Strategic AI Coding

**Podcast:** The Startup Ideas Podcast
**Published:** 2026-02-06

## Transcript

Today's a massive day because Anthropic just dropped Opus 4.6 and OpenAI answered with GPT 5.3 codex.
But what is the better model and how do you get started?
And what are some tips and tricks to get the most out of them?
Well, this episode is all about that.
This is for the technical person who's trying to get the most out of these models, who don't just want hot takes, who want tactical sauce for getting the most out of these models.
This episode of the pod is with my dear friend Morgan Linton.
Morgan is one of the best engineers I know.
He was an executive at Sonos.
He's invested in a lot of AI companies, and he's building an AI company of his own.
He's one of my first calls when I'm like, hey, which model's better?
So we put the models head to head, and there's a winner at the end.
We rebuild Polymarket, a multi-billion dollar app, but we use these models.
So which is the better one?
You'll find out by watching this episode.
But you'll also learn to become a better AI developer because you'll have these tips and tricks in your back pocket.
He's does it all, but today what you know what I I needed him to help me understand is Opus 4.6 just came out.
GPT 5.3 codecs just came out.
Morgan, help me understand by the end of this episode, what are people gonna get out of this?
Yeah.
Well, Greg, thanks for having me.
Super exciting day.
It's moving fast today.
Opus 4.6 came out, and then Sam Altman put together a quick tweet.
I wanna say, like maybe 18 minutes later, announcing GPT-5.3 codecs.
Uh, and me, I think everybody else has been jumping on it, playing around, figuring out the differences.
Um, you know, all the little neat new settings that there are in each of these.
By the end of this, you're gonna know first how to make sure that you are running Opus4.6 and all of the little details you can change in the settings.json file to use some of the cool features in Opus 4.6, especially agent teams, which is probably the feature I'm the most excited about.
Um it'll also understand why you might use one versus the other, because they both kind of tackle different engineering methodologies.
Um, and then hopefully you'll see some cool stuff as we build some demos together that I've put together that I haven't tried myself, so I'll be trying just live with you.
So we'll we'll see how that goes.
Cool.
I think one of them is we're gonna try to recreate polymarket.
Yes, and see which model performs best.
Yeah, we're gonna have both, they're gonna do a head-to-head to try to each build their own version of PolyMarket.
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.
Cool.
Right on.
All right, so I took some notes and essentially, you know, with 5.3 codecs um, 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 if OpenAI was wanting a demo to be done the right way, they would want me to do it in their app.
Um, 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 um 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, uh, it's weird, I'm having a problem, like I'm 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 Opus46.
How do I make sure I'm doing that and doing that correctly?
Um, so here's kind of the initial to-dos that everyone should have on their list.
Just do an NP NPM update, see if that does the trick.
Um, if that doesn't, and you're running an older version, um, then run claude update.
But you you should see, like as of right now, it's 2.1.32.
If you see one dot something, you're running an old version.
Um, 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 C D uh tilde slash uh dot claude.
So I bet that there's people who are running the old model, they don't even realize it.
Probably bad bad.
No idea.
Yeah, yeah.
So I mean, make sure you go in here, cd tiltaslash.claude.
Here's your settings.json.
Um if you view this, here's essentially what you should see.
Um now it's okay, it can be model.
If you want to like really be specific about it, you can put in claude-opish dash four-six.
That'll lock it in.
But because four six is the newest model, you can also just put in model and just opus and that'll work.
Um, the key thing that you want to do is the in my opinion, the coolest feature that they added with 4.6 is agent teams.
I'm super excited to demo that with you.
Um, you have to make sure to turn that on because it is an experimental feature.
And that's probably the biggest confusion I'm seeing people have today with Opus46, 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 end this claude code experimental agent teams and then set it equal to one.
Okay.
Nothing too crazy.
Once you do that, that will uh make all that possible.
Uh so with that in mind, um, you're pretty ready to go there.
Then you can just run claud 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.
Um, this is in the API.
This is not in Claude Code itself.
Uh, but adaptive thinking, just to show it here, uh, you're able to essentially pick the uh 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 a different level.
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 to 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 worth mentioning.
And then uh kind of the last the last thing I would say is uh just uh if you want to use split panes for agents.
So if you want agents to show up in different panes, um, and you're using something like warp, just make sure to install tmux.
You can do this with Brewinstall Tmux, and then um if you do that, it's gonna default to auto, uh, which usually means in process, which means in that same terminal window you have, the agents are gonna be working um all together.
If you want it to split pane, then you just need to update uh that setting and the settings.json to split panes.
I'm not gonna 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, uh 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.
Cool.
So that's that.
Before I get into kind of the differences between uh Opus 4.6 and Codex, I thought I would actually read this because uh 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 because I think they do such a good job with it.
This person's saying what's interesting to me is that GPT 5.3 and Opus 4.6 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 and help 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 4.6 is better, uh, codex is it's it's different.
It depends on what your methodology is.
And I think what we're seeing now, um, 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 that's where you're now seeing a divergence, where I think you're gonna see a lot of teams using both because Codex really is your collaborator.
And what they've added with 5.3 is like really good like mid execution steering.
Whereas 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, and don't bug me.
I want to trust they're gonna do good stuff.
Um, and it's able to deliver.
So, are you saying that they're in some ways it's just a preference, like depending on how you know there's no right or wrong, basically.
You know, you know, it're not wrong to be an Opus person or you know, it just like might feel yeah, it might it's just a preference.
Yeah, well, and you might be both.
Right.
That's true.
It might turn out that you're both.
That's why, like, not to disappoint people here, but we're not gonna 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 um 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 uh playing around with both of these and having them do a head-to-head and try to build a competitor to polymarket in however much time we have.
Um, but uh I'll just I'll just start kind of going into these uh at a high level, just so for anyone who wants to know like what are the core differences, why is this so interesting?
Um just go into what that is.
So with with Opus 4.6, uh much bigger context window.
So you have a million token context window here.
Um very strong coherence over entire documents and repos, uh, designed for you know, like load the whole universe and reason over it.
Uh five three, 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 number is around 200,000 tokens, which is not that impressive.
That's smaller than I was thinking it would be.
Um, but that's okay.
It's optimized, you know, for for progressive execution rather than total recall.
So that's why that's not as important.
Um, and you know, optimized for deciding like 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.
Uh GPT Thrive 5.3 codecs is probably better when the task is decide fast, act, iterate, more of that, you know, paraprogramming, you know, mid task change uh behavior.
For uh for coding benchmarks, you know, Opus 4.6 is really good at code base comprehension, um, refactors with like architectural sensitivity, explaining why a system behaves a certain way, uh, and then you know, a little less tendency of this like YOLO write code, right?
That's good.
Uh which is I think something everybody wants.
Yeah, exactly.
Um, so you know, that's good for everybody, but especially for um vibe coders that are getting started and they may not be able to identify hallucinations.
Opus 4.6 is definitely gonna perform better there.
But then for teams, you know, building in large code bases like like like me and my team are doing, um, that's also really important.
So kind of a win for everyone there.
Five 5.3 codecs did win on SWE Bench Pro, Terminal Bench.
Overall, overall it's like scored better on coding benchmarks.
So probably better end to end-to-end app generation.
And you know, Claude's kind of like senior reviewer staff engineer.
Uh GPT 5.3, probably like your your founding engineer, right?
Uh agentic behavior, uh, Opus 4.6, this is the key one, right?
Is like the multi-agent orchestration.
Um, that's that's probably like the bleeding edge feature in 4.6.
Um, and then with uh with with uh 5.3 codecs 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.
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 it sort of knows what it did.
Um, but you know, Claude's really asking, like, should we do this?
GPT GPT 5.3 is like, how fast can I ship this?
Right.
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.
Yes, totally.
Yeah, it's a good way to look at it.
It's like a different, it's like a different personality type, right?
And then yeah, uh failure failure modes, uh, you know, Claude 4.6, it might overanalyze, it's got a much bigger context window.
Uh, it can hesitate when when requirements are ambiguous, and then it can stop short on uh full execution.
Uh 5.
Five three codecs, uh could be overconfident, can lock in a flawed assumption early, but you can steer it back in the right direction if that if that happens.
So that's kind of a high level overview on the on the two.
Cool.
That's helpful.
Yeah.
So should we should we just dive in?
I haven't tested any of this.
So this is now I have like zero canned demos because I thought it'd be more fun just to uh try something together and see what happens.
So should we should we try it?
Yeah.
Okay, so let's see.
I'm gonna um I'm gonna start with Opus, and I've got these prompts preloaded.
So I'm giving different prompts, just like I think you 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 gonna give to Opus is build a competitive poly market, create an agent team to explore this from different angles.
One teammate on technical architecture, one on understanding poly market 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 codecs, I'm gonna give it a little different prompt, but very similar.
So still build a competitive poly market, 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 gonna try to paste these in around the same time.
Um you're a fair guy, Morgan.
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.
It's it's just about uh just about letting everybody have a fair shot to play the game.
Yeah, uh right.
So let's see, I'm gonna make different directories for you.
So I'll do uh let's just call this opus four five polymarket competitor.
All right, so let's fire up Claude in here.
By the way, if you want to check when you're running, uh, just to like really make sure that you're in a good place with the model.
If you type /model, I can see here, right?
Claude Opus 4.6.
Right.
Um, so I'm good there.
I'm gonna take this prompt, copy it.
Make sure this is all copied in correctly.
Okay, got that.
I'm not gonna hit enter yet.
I'm making this totally fair.
I don't want anyone at anthropic or open AI to get upset with me.
So I want to be in good terms with both of them.
Totally.
Smart guy.
Let's see.
Oh, wait, actually, you know what?
I do want to create a new 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 with the eye.
I'm not, I'm not, I'm not or open AI.
Nope.
Yeah.
Nope.
I love them both equally.
How about that?
Yeah.
Okay.
And I'm gonna try to start them as close to on the same time as I can.
Enter, go.
All right, they're going.
Off the races.
So what do you think's gonna happen?
That's a great question.
Well, I know right now, because I told uh Opus 4.5 to build uh using different teammates, it's gonna 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 plan and code base.
This is brand brand new, right?
Like if I did this with Opus yesterday, wouldn't be possible.
Um, that's kind of the difference here is that um the way that um 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 gonna launch all these different agents and compare what they say.
It's say, okay, I'm gonna inspect the workspace.
This is your, you know, really detail-oriented, really senior like founding engineer, like that example gave, right?
Whereas over here you can see it's already launched these agents, and now it wants to do web searches, and I'm gonna let it do that.
So multiple agents were asking to do web searches.
So 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's 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's looking at polymarket, how it works, barn and 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 gonna go to poly market, and let's really hope the polymarket doesn't block it, because that'll make things harder for it.
Meanwhile, over here, uh this has discovered codex.
We figured out the repo's empty, so it's gonna scaffold it from scratch.
Um, 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 uh codex is out here building and is is like building the engine.
Uh with Opus 4.6, it still has agents out there like doing research work.
Yeah, you really start to see just like how different they really are as they make progress.
Yeah.
Like I said, I haven't tested it before, so we don't know how long it'll take each of these.
Totally.
Yeah, and I think like I guess one question I I have is like, is one is one model better for being more of a beginner vibe non-technical vibe coder, or you know, doesn't really matter.
Yeah, it's a good question.
I mean, I think the fair answer would be probably codex, because codex uh edged out Opus 4.6 a little bit on some of those coding benchmarks and is is kind of known for writing better production code.
Probably codex in that way.
Um at the same time, one of the downsides, and like I said, this is uh I could only do this in a totally balanced way because they're so different.
Um, you know, at the same time for a uh a vibe coder knowing when to interject and stop codecs and say, oh wait, you're doing this this way.
Uh can you instead look at doing it this way?
They're probably not gonna 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?
Yeah.
Okay, uh Codex is done.
All right.
Um, so codex built a competitor to PolyMarket in three minutes and 47 seconds.
And to be clear, Polymarket's a multi billion dollar company.
Yeah, I don't think this will work quite as well.
Um, but uh, but we'll see.
Let's see.
So um let's just check out if it worked first.
I'll let this keep running here.
Um 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 uh test suite.
And it passed with 10 out of 10 tests.
Uh as far as what it built, it has this core LMSR uh market maker engine.
So coherent pricing, slippage, bound loss behavior, uh 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 uh obviously any of this in any way.
It figured out the architecture on its own.
Uh clean responsive front end.
All right, well, let's see.
Let's see if it is actually.
So um 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 gonna do NPM test.
All right, tests 10 past 10.
That looks good to me.
Oh, yeah.
NPM start.
All right, it's running.
Uh let's see.
Okay, here we go.
Uh so this looks like it has the ability.
So let's, Greg, let's make you uh we'll make you the first trader.
All right.
Okay.
Uh say add.
Okay.
You got a thousand bucks.
Okay.
There we go.
Not bad.
All right.
What uh what market do you want to create?
Um, well, Bitcoin, I think as we speak, has crashed to what 63,000 or something?
Something like that, yeah.
So I do like the I mean, will BDC be about, you know, be above 110K by Yeah.
Okay.
By DES 31.
Yeah, okay.
So let's I mean that's almost double.
Yeah.
That'd be pretty good.
It depends.
It depends.
Depends when you bought it, you know.
If you bought it at uh 20225k, then you're not so happy, but let's see.
So then I don't know, I don't even know what resolution criterion source would mean be.
I mean, I think I know what it's getting at, but I guess you could say like uh uh why don't we say use coin market uh cap as the source and resolve by looking at the price uh on the last day of December uh just before midnight, I guess.
Yeah, I guess like uh uh the price of BTC.
Yeah, all right.
Okay, it looks like it's okay.
So we've got it now.
So we'll use CoinMarket Cap.
Okay.
So then you could do a yes, 50%.
So what what do you think?
Yes, yes, or no.
I mean, this isn't financial advice.
This is just purely for educational purposes, but I think I think so.
I think that.
All right, that's a yes for Greg.
Buy.
Um, let's see.
Uh how many shares you want to buy?
You've got a thousand bucks.
Um I want to put it all.
Um I'll put it all on this.
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, you know, as a prototype, relatively uh functional here.
I I guess that it actually has decremented.
So okay, a thousand shares was not that ended up being uh, you know, about 24 that you spent.
So you've got more money if you wanted to create another market.
Um, but it worked, it's not returning an air.
It shows the volume here.
Um, interesting.
All right, so let's go back.
Let's see.
So far, so good with that, I'd say.
Uh 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 uh opus is, and uh it's very token hungry.
Each one of these agents has used over 25,000 tokens.
Um let's see though.
So they finished, right?
The the the technical research around architecture is done.
Prediction market research is done.
The UX design research is done, the testing strategy is done.
Uh now it's gonna go and build.
So it's writing the package, JSON.
Did you see the ad that anthropic launched about uh ads?
Yes, I watched them all.
They're hilarious.
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 uh I also I found them hilarious, but I also understand his side as well.
So it seems like anthropic is sort of anti-ads for now, and and obviously chat GPT is gonna be introducing ads.
Yes.
And you know, when I'm when I'm watching this and I'm seeing you're going through 25,000 tokens, 25,000 tokens, 25,000 tokens.
Yeah, I'm like, yeah, of course, anthropic doesn't really exactly 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 uh in doing this.
So I think that's one of the very good things uh for like investors in anthropic, right?
Is with agents and agents now being, I think, probably the new killer feature in Opus.
Yeah, you're gonna take whatever token usage and multiply it by the number of agents.
Exactly.
It's actually really smart.
And I wonder if that was like the thinking.
Like they're like, how can we get people to use more tokens?
Oh, we'll just like spin up agents and we'll design it like that.
Or do they think like, okay, how can we design a system that is best for the use case?
And then they're like, okay, then we'll monetize it like this.
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.
100,000 tokens is like roughly how much in US dollars.
I don't know because I have a I have a um Claude Max plan.
200 bucks.
So yeah.
So I'm not paying it.
We're not seeing it hit any limits right now, right?
So I'm not paying more than 200.
I can tell you that.
Yeah.
My guess is it's you know, we're talking like in in the 200 max pen.
Do you remember how many how many tokens you get approximately?
That's a good question.
Um let me check.
Can you fire up, let me fire up Claude and ask it?
Let's see here.
How many tokens do uh get estimate?
Let's see.
Okay, so here you go.
Estimate estimates.
So uh 45 million tokens per month of Sonnet, but let's see.
Uh what is your estimate for Opus or six?
It's like they don't really want you to know.
No, they're trying to make it a little harder.
Okay.
Well, yeah, they're not even gonna tell me actually.
They're just gonna say there's no public data, it's very new.
Opus is roughly five X more expensive.
So then uh if it's 45 million, that's five X, so 10 million is probably the answer.
About right.
Yeah, yeah.
Um so then if we're doing, you know, quick math, let's just say we spent 100,000 tokens.
Um, you know, 100,000 divided by 5 million is you know, we're not gonna spend more than that because look at this.
We're we're now over 17,000 tokens on top of that in this next build.
Okay.
So, but still, let's say, you know, even if we use a million tokens building a competitor to pay market right now, uh, we're still only using a tenth of what it buddy can do.
That's not terrible.
No, I mean it's 20 dollars, which is like the price of a cocktail in Miami.
Yeah, yeah, exactly.
Yeah, yeah.
So let's see.
But now for as I say, I'm watching the tokens uh creep up.
Right, so it's building the API routes now.
I have a feeling this is gonna be a better end result.
I 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 it feels like we're gonna see something very different when we uh when we load what it builds.
Yeah.
I don't think we gave it any like design, like visual design, any, you know.
So no, do you recommend for folks to just like sort of get the MVP app out, play around with it on local host, you know, click some buttons and then sort of update with the visual design from there?
It's a good question.
I I do like 5050.
Sometimes if I have something in mind, yeah.
Um, especially if I want something like on brand with something, like suppose I'm building something that is um gonna be in the like open claw multi book ecosystem.
I would probably say, hey, I want to design a site that uh you know looks somewhat similar to or is inspired by, you know, uh 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.
Cool.
I'm really excited to see what this is doing, though.
I think we're we're now like well over 200,000 tokens, based on what I could tell.
Uh, but we're not at 10 million.
We're not hitting any limits, you know, we don't have to take out a second mortgages on our and yet.
Yeah, it's still going so I guess you know we can tell.
Like, here's an interesting thing.
Um, in a comparison, like this is still going.
Uh why don't we say like uh the design, because the design looked kind of bland to me, right?
Yeah, yes, it did.
Uh can you spruce it up and make it look nicer?
Because like we may as well have codex working away too, right?
Yeah, so you bait you didn't really give it any like specific, it should look like square.com or no.
So we'll see.
We'll basically see if if codex, if you know, five if 5.3 has a little bit of taste.
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.
Um it's editing um index.html.
It looks like he's gonna add motion hover polish.
Okay.
Two look at that.
This current task we're over 30,000 tokens, building the front end UI.
Okay, it's done.
Yeah, codex is fast, by the way, right?
I mean, that's pretty darn fast.
Yeah.
Um, 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.
Not that different.
It's yeah, I think um can I try something?
Yeah, go for it.
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.
There you go, yeah.
And then I'm gonna say pretend you are Jack Dorsey.
And how would he design this website to be clean, elegant, and full and full of interesting interactions?
Yeah, great.
Yeah.
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 the first one guy who came to mind or first person came to mine.
So 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 card.
Okay.
You know what's interesting is it didn't.
I would have kind of hoped, and maybe we, you know, we're not quite out of 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.
Exactly.
Um, I'm surprised it's not doing that.
Instead, it's going like, I 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 it's really just taking like this part of your question and going, oh, okay, major refresh, I'll do that.
Well, can it can't you ask it?
Can't you say, do you know who Jack Dorsey is?
Let's see.
I can actually uh 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.
It's thinking about it.
43,000 tokens over here.
Okay.
Yes.
Okay, here we go.
Yes, Jack Dorsey is the co-founder of Twitter, former Dock and Square.
Okay, with a design style that's typically minimal restrained and interaction focused.
Beautiful.
Okay.
All right.
So touche.
It showed us.
Yeah.
Now here's the weird thing.
It looks like it's a complete, or do we have to say complete?
Like right when I was saying that.
Like, are you done?
Or did you stop because I asked a question?
Yeah, this is really interesting.
I will say, like the oh, I pause when you ask the question.
The major redesign.
Oh, interesting.
Mostly if you want, I'll resume.
Oh, so that's weird.
So you ask it a question, it just stops, but like uh, so like, yes, of course, continue.
Yeah, okay.
So that's uh that's actually some weird UX.
Like it obviously should just continue after.
Right?
Yeah.
I would assume that it's such a weird thing because it said, Yeah, if you want, I'll resume now.
I will say, I I do like that you can in midstream, like kind of edit things.
Yeah.
Like that's how my brain works.
Totally.
Personally.
Yeah, yeah.
This is using a ton of tokens.
Yeah, it is amazing to see the detail.
I mean, this this should be a work of art, whatever site this comes off with.
Um, this is done.
So now let's see.
We can go back to this.
And uh I mean, I'm not blown away, but it's okay.
Opinions become price in milliseconds, trade conviction, not noise.
Signal market is designed for fast thesis iter iter iteration with transparent pricing.
Okay.
I mean, I I I would push it more, I think.
Yeah.
Yeah.
I guess, yeah, like I would say go for it.
I would say that's not the Jack Dorsey I know.
I don't know, Jack Dorsey.
Uh I was looking for a caps lock major upgrade.
Uh that that might mean um way more copy, way more images, yeah.
Way more storytelling.
Yeah, exactly.
Et cetera, et cetera.
Yeah, I'll just say seriously, take your time, go nuts.
Yeah.
What are credits?
Famous last words more, Morgan.
Yeah, I know, right?
It's like, oh, perfect.
Okay.
That's like a signal within the opening headquarters, like, we finally got someone.
Totally, it's a whale.
All right.
So Opus has finished.
Yeah.
I have no idea how many credits that use, but probably actually let me ask it.
How many uh how many tokens in total did you use to put all of this together, including the four agents.
And then we can open using tokens to answer.
That's so funny.
Okay.
Uh doesn't know.
Let's see.
Okay, here we go.
Okay, it's it's estimating.
It actually doesn't know, which is weird, because it should know.
Although uh wonder if I can actually do slash cost.
Oh, here we go.
Yeah, okay.
Oh, it doesn't know.
No need to monitor cost.
Okay.
Yeah, no too.
Um okay, it's guessing 150 to 250,000 tokens total.
Yeah.
That's probably right.
Okay, sure.
Yeah.
Okay, so here's what it's done.
So first off, one really interesting thing here is um, you know, Codecs created 10 tests, right?
Uh Opus created 96 tests.
So definitely a lot uh a lot more detail on the testing side.
And it's called it forecast, uh, whereas uh Codex called it uh 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 GS14 app router, central limit order book, uh database schema wrestle API.
Okay, the prediction market domain expert, binary yes, no market where yes no is always a dollar.
Okay.
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 down order book test, matching engine, okay.
Uh all right.
NPN run dub to start the app.
So let's go in here.
And oh, interesting.
Okay.
I don't want to say anything, actually.
I've already given it to me.
What's your initial take?
I mean, my uh hello, Jack Dorsey.
You know what I'm saying?
This is this is what I expected it to look like when we pushed Codex.
Yeah, me too.
Um this looks really clean.
What happens when you hover over uh oh yeah, look at that.
Yeah, it's got hover states.
Yeah.
Um it's obviously got it organized.
Like when I go sports, you know, will the next tube will have over 120 million viewers?
Will AI pass the Turing test by 2027?
Will a movie preserve three?
It's got stuff in there, yeah.
Yeah.
This doesn't even it doesn't feel like an MVP.
Yeah.
This is pretty wild, actually.
And it created some stuff, you know, that we never talked to it about, right?
Like a looter board.
Um, which it's already populated with some initial stuff.
Portfolio section.
Yeah.
Interesting.
So let's see now.
So I mean, I'm I'm more impressed with the it was maybe worth the 150,000 250,000 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.
Huh?
This is this is insane, bro.
That's clean.
That's clean.
Yeah.
I wasn't expecting to click in and actually get a well-designed 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 gonna be able to sign in because I haven't set anything up.
Let me just check.
Uh well, you can sign up, says don't have an account.
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 gonna take the username Greg.
I'll instill your username.
All right.
Uh let's see.
Okay.
So yeah, it's probably because I was gonna say the database isn't wired up yet.
So I'm not I'm not surprised that I would actually have to do.
I wasn't expecting to do that.
So um, but I get it.
I mean, it's clean.
This is pretty neat.
Yep.
Um, yeah.
All right, let's see.
So then Ken this, all right.
We've given, I don't know about you, but this is the last chance I'm gonna give Codex on the design side.
Um, it's out of it's out of opportunities here.
So um, oh here, it's funny though.
In the in the end, it kind of it's it's acting a little bit like data from Star Trek.
I mean the question, what are credits?
In this context, credits usually means uh 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.
Boom.
Oh.
Oh, okay.
This is getting a little bit interesting.
Let's see here.
Read the manifesto.
Yeah, I mean, I don't hate it.
It's definitely better.
Yeah.
I mean, it's it's got a lot going on.
Yeah.
But it's different.
Terminal.
It's different than uh yeah, it's 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.
This is so good, it's so fast.
Yeah, yeah.
I mean, I I would say, you know, like I said, I'm not gonna say which one is it's not that opus is better than codex or vice versa, but I I would say in this test, opus one.
Yeah, in this test, Opus One.
Yeah, that's just the truth.
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?
Yeah.
Yeah.
Yeah.
Well, anything else you wanted to cover?
Um, 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.
Yeah.
Um let me see if there is anything else in here.
I covered the adapted thinking.
Oh, I guess just on the um orchestration, I would say, you know, this is a feature I'm probably the most excited about with Opus.
And clearly we saw in this example it working really well.
Um, just make sure to look at the documentation.
It's all in the docs now.
Um, and it gives some examples as well.
Because it has this idea of like compare with subagents of like context and communication and coordination and kind of breaks this down.
Um, and then it has like a sample prompt, uh, 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 gonna want to dive in and use um use agents with Opus 4.6, and they've got pretty good details on all the little uh tweaks that you can make with it.
Amazing.
Well, Morgan, I can't thank you enough for coming on.
I I hope people love this episode.
Um I love talking to you.
You get thank you for having me, Greg.
It's a total honor.
You're uh yeah, it's just I love how clearly you communicate and and and uh to technical people but also non-technical people and you're criminally underfollowed.
So I'm gonna include the link where you can find Morgan and follow him on X.
He talked 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.
Yeah I mean I'm the the co-founder and CTO of bold metrics um I'll just give a little plug for us we have uh uh 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 uh machine learning models that update and adapt over time to help people find the right size and give lots of really interesting data to lots of amazing brands and retailers that you probably all know and love and and 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 uh Opus 4.6 and 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 um to do better, more creative work.
Yeah, stop listening to us right now.
Like exactly stop listening to us.
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.
Morgan, thanks again for coming on the show.
Um, this was a lot of fun.
See you next time.
Thank you so much.
Total honor.