← Back
Nate Herk July 10, 2026 20m

I Tested GPT 5.6 Sol vs Fable 5. What You Need To Know.

Read full transcript 16 segments
  1. So, we finally have GBT 5.6 Soul, Terra, So, we finally have GBT 5.6 Soul, Terra, and Luna. And the benchmarks are and Luna. And the benchmarks are and Luna. And the benchmarks are insanely impressive because it basically insanely impressive because it basically insanely impressive because it basically shows that Soul blows Opus and Fable out shows that Soul blows Opus and Fable out shows that Soul blows Opus and Fable out of the water and is significantly of the water and is significantly of the water and is significantly cheaper. So, I'm going to quickly flash cheaper. So, I'm going to quickly flash cheaper. So, I'm going to quickly flash a few of these benchmarks on screen a few of these benchmarks on screen a few of these benchmarks on screen right now, but I don't want to just talk right now, but I don't want to just talk right now, but I don't want to just talk about the benchmarks. I think that's about the benchmarks. I think that's about the benchmarks. I think that's extremely boring. I've been playing extremely boring. I've been playing extremely boring. I've been playing around with these models all day long. around with these models all day long. around with these models all day long. I've been putting them side by side, I've been putting them side by side, I've been putting them side by side, meaning GBT 5.6 and Fable 5. and I've meaning GBT 5.6 and Fable 5. and I've meaning GBT 5.6 and Fable 5. and I've been driving my day-to-day work with been driving my day-to-day work with been driving my day-to-day work with these two models so I can actually tell these two models so I can actually tell these two models so I can actually tell you which model do I like for which use you which model do I like for which use you which model do I like for which use cases and why. So, don't want to waste cases and why. So, don't want to waste cases and why. So, don't want to waste any of your time. Let's just get any of your time. Let's just get any of your time. Let's just get straight into today's video. Now, real straight into today's video. Now, real straight into today's video. Now, real quick before we hop in, I did want to quick before we hop in, I did want to quick before we hop in, I did want to call out that I do think that this call out that I do think that this call out that I do think that this landing page is pretty awesome. I love landing page is pretty awesome. I love landing page is pretty awesome. I love the Soul and the Terra and the Luna back the Soul and the Terra and the Luna back the Soul and the Terra and the Luna back here. And you can see that there's here. And you can see that there's here. And you can see that there's little fives and sixes kind of like little fives and sixes kind of like little fives and sixes kind of like drifting all over and inside of these drifting all over and inside of these drifting all over and inside of these planets as well, which I thought was a planets as well, which I thought was a planets as well, which I thought was a nice touch. But anyways, let's get into nice touch. But anyways, let's get into nice touch. But anyways, let's get into what I actually did today. All right. what I actually did today. All right. what I actually did today. All right. So, I'm just going to walk you guys So, I'm just going to walk you guys So, I'm just going to walk you guys through some of the experiments I did through some of the experiments I did through some of the experiments I did and then at the end I'm going to and then at the end I'm going to and then at the end I'm going to actually talk about like the pros and actually talk about like the pros and actually talk about like the pros and cons of each and my overall consensus. cons of each and my overall consensus. cons of each and my overall consensus. So, the first thing I did, I have Claude So, the first thing I did, I have Claude So, the first thing I did, I have Claude on the left here with Fable 5. I've got on the left here with Fable 5. I've got on the left here with Fable 5. I've got Codex on the right here with GBD 5.6 Codex on the right here with GBD 5.6 Codex on the right here with GBD 5.6 Soul. And I gave them both the exact Soul. And I gave them both the exact Soul. And I gave them both the exact same prompt. So, I gave them both a/goal same prompt. So, I gave them both a/goal same prompt. So, I gave them both a/goal and I told them to build a genuinely fun and I told them to build a genuinely fun and I told them to build a genuinely fun playable open world bike game that runs playable open world bike game that runs playable open world bike game that runs in the browser. I gave them these other in the browser. I gave them these other in the browser. I gave them these other rules. I'm not going to read off this rules. I'm not going to read off this rules. I'm not going to read off this whole prompt, but if you want to take a whole prompt, but if you want to take a whole prompt, but if you want to take a look, feel free. I gave them creative look, feel free. I gave them creative look, feel free. I gave them creative freedom and I just wanted to see what freedom and I just wanted to see what freedom and I just wanted to see what they could come up with. Okay, so I they could come up with. Okay, so I they could come up with. Okay, so I haven't played any of these yet, but I'm haven't played any of these yet, but I'm haven't played any of these yet, but I'm not going to tell you which one's which.

  2. not going to tell you which one's which. not going to tell you which one's which. We're gonna see them both and then I'll We're gonna see them both and then I'll We're gonna see them both and then I'll reveal. So, WD to steer, space to bunny reveal. So, WD to steer, space to bunny reveal. So, WD to steer, space to bunny hop, Q and E for air tricks, shift for hop, Q and E for air tricks, shift for hop, Q and E for air tricks, shift for boost. Okay, let's go ahead and drop in. boost. Okay, let's go ahead and drop in. boost. Okay, let's go ahead and drop in. Nice. Okay, so we can move around. We Nice. Okay, so we can move around. We Nice. Okay, so we can move around. We have a city here. The camera's a little have a city here. The camera's a little have a city here. The camera's a little bit hard to maneuver with. Um, you can't bit hard to maneuver with. Um, you can't bit hard to maneuver with. Um, you can't drive through the building, so that's drive through the building, so that's drive through the building, so that's good to know. Okay, just got a little good to know. Okay, just got a little good to know. Okay, just got a little trick in the air there. So, this is trick in the air there. So, this is trick in the air there. So, this is honestly working pretty well. I don't honestly working pretty well. I don't honestly working pretty well. I don't love the actual way that this works. love the actual way that this works. love the actual way that this works. Like the top down bird's eye view, I Like the top down bird's eye view, I Like the top down bird's eye view, I don't think I like. It's a little bit don't think I like. It's a little bit don't think I like. It's a little bit hard to control, but hey, hard to control, but hey, hard to control, but hey, functionality-wise, the coins are functionality-wise, the coins are functionality-wise, the coins are working, the controls work. I just working, the controls work. I just working, the controls work. I just jumped over a building and I can bunny jumped over a building and I can bunny jumped over a building and I can bunny hop. Okay, cool. And it doesn't look too hop. Okay, cool. And it doesn't look too hop. Okay, cool. And it doesn't look too bad either, considering this didn't take bad either, considering this didn't take bad either, considering this didn't take it very long. So, that was the first it very long. So, that was the first it very long. So, that was the first game. All right, and now here is the game. All right, and now here is the game. All right, and now here is the other version. Let's go ahead and see. other version. Let's go ahead and see. other version. Let's go ahead and see. It's pretty similar controls. So, let's It's pretty similar controls. So, let's It's pretty similar controls. So, let's hop in here. Okay, so this one is more hop in here. Okay, so this one is more hop in here. Okay, so this one is more like a 3D almost more of like a POV sort like a 3D almost more of like a POV sort like a 3D almost more of like a POV sort of style. I can jump. I can spin. Oh, I of style. I can jump. I can spin. Oh, I of style. I can jump. I can spin. Oh, I don't know what just happened there. Um, don't know what just happened there. Um, don't know what just happened there. Um, but I'm in a city. I've got the coin but I'm in a city. I've got the coin but I'm in a city. I've got the coin still. Let's see if I can go try to get still. Let's see if I can go try to get still. Let's see if I can go try to get on this ramp and see what the uh the on this ramp and see what the uh the on this ramp and see what the uh the physics of that look like. Wait, am I on physics of that look like. Wait, am I on physics of that look like. Wait, am I on the wrong side of the ramp? Yep, that the wrong side of the ramp? Yep, that the wrong side of the ramp? Yep, that was the wrong side of the ramp.

  3. was the wrong side of the ramp. was the wrong side of the ramp. But this definitely has more of like But this definitely has more of like But this definitely has more of like that I don't know, like more of a GTA that I don't know, like more of a GTA that I don't know, like more of a GTA vibe, like an open world game that you vibe, like an open world game that you vibe, like an open world game that you can actually like I don't know, explore. can actually like I don't know, explore. can actually like I don't know, explore. It feels like the map is much bigger. I It feels like the map is much bigger. I It feels like the map is much bigger. I mean, this is definitely a clear winner. mean, this is definitely a clear winner. mean, this is definitely a clear winner. So, I think that we've decided that. All So, I think that we've decided that. All So, I think that we've decided that. All right. So, in this example, the second right. So, in this example, the second right. So, in this example, the second one, which is the one I thought was the one, which is the one I thought was the one, which is the one I thought was the winner here, was Fable 5. So, that's on winner here, was Fable 5. So, that's on winner here, was Fable 5. So, that's on the left hand side here. This took 21 the left hand side here. This took 21 the left hand side here. This took 21 minutes and 37 seconds, whereas the minutes and 37 seconds, whereas the minutes and 37 seconds, whereas the other side um GBT Soul took 23 minutes. other side um GBT Soul took 23 minutes. other side um GBT Soul took 23 minutes. So, similar on the timing here, but So, similar on the timing here, but So, similar on the timing here, but let's look at cost. So, this Fable run let's look at cost. So, this Fable run let's look at cost. So, this Fable run would have costed me about $14.22, 22 would have costed me about $14.22, 22 would have costed me about $14.22, 22 whereas the GBT Soul run would have whereas the GBT Soul run would have whereas the GBT Soul run would have costed $4.5. Now what I think is really costed $4.5. Now what I think is really costed $4.5. Now what I think is really interesting here is the output tokens. interesting here is the output tokens. interesting here is the output tokens. Fable outputed about 90,000 and Soul Fable outputed about 90,000 and Soul Fable outputed about 90,000 and Soul only outputed about $31,000. So we've only outputed about $31,000. So we've only outputed about $31,000. So we've consistently seen that Codeex and GBT consistently seen that Codeex and GBT consistently seen that Codeex and GBT are way more token efficient and are way more token efficient and are way more token efficient and sometimes that's better and sometimes sometimes that's better and sometimes sometimes that's better and sometimes that's not. In this case I would say that's not. In this case I would say that's not. In this case I would say that it wasn't better because Fable's that it wasn't better because Fable's that it wasn't better because Fable's output in my opinion was like not just a output in my opinion was like not just a output in my opinion was like not just a little bit better, it was significantly little bit better, it was significantly little bit better, it was significantly better. All right, so let's move on to better. All right, so let's move on to better. All right, so let's move on to the second test. So this one was kind of the second test. So this one was kind of the second test. So this one was kind of similar. I just said, "Hey / goal, build similar. I just said, "Hey / goal, build similar. I just said, "Hey / goal, build me the most impressive interactive me the most impressive interactive me the most impressive interactive scroll stopping website that you can scroll stopping website that you can scroll stopping website that you can imagine." So, I gave them complete imagine." So, I gave them complete imagine." So, I gave them complete creative freedom. I just wanted to see creative freedom. I just wanted to see creative freedom. I just wanted to see what the models did with that. So, let what the models did with that. So, let what the models did with that. So, let me pull up both versions once again. All me pull up both versions once again. All me pull up both versions once again. All right. So, once again, not going to tell right. So, once again, not going to tell right. So, once again, not going to tell you which one is which. I want you to you which one is which. I want you to you which one is which. I want you to try to form your own opinion. This one try to form your own opinion. This one try to form your own opinion. This one also has sound with it. So, I will make also has sound with it. So, I will make also has sound with it. So, I will make sure the sound is turned on. So, what sure the sound is turned on. So, what sure the sound is turned on. So, what you can see here is 10 billion years.

  4. you can see here is 10 billion years. you can see here is 10 billion years. And as we scroll down, we're going to And as we scroll down, we're going to And as we scroll down, we're going to get like kind of a journey, but get like kind of a journey, but get like kind of a journey, but everything in the background is pretty everything in the background is pretty everything in the background is pretty interactive. So, it's very like 3D. So, interactive. So, it's very like 3D. So, interactive. So, it's very like 3D. So, watch as I scroll down here. We start watch as I scroll down here. We start watch as I scroll down here. We start off with the cloud. Not too much, but off with the cloud. Not too much, but off with the cloud. Not too much, but you can still see that there's, you you can still see that there's, you you can still see that there's, you know, like um responsiveness to my mouse know, like um responsiveness to my mouse know, like um responsiveness to my mouse movements. Then we have the collapse. movements. Then we have the collapse. movements. Then we have the collapse. And once again, we've got some cool like And once again, we've got some cool like And once again, we've got some cool like galaxy looking, very 3D. And basically, galaxy looking, very 3D. And basically, galaxy looking, very 3D. And basically, that's the theme of this whole thing. that's the theme of this whole thing. that's the theme of this whole thing. It's telling the story, I guess, of It's telling the story, I guess, of It's telling the story, I guess, of like, you know, how we got to where we like, you know, how we got to where we like, you know, how we got to where we are. This is a pretty cool effect. Um, are. This is a pretty cool effect. Um, are. This is a pretty cool effect. Um, first light and um first light and um first light and um the swelling, so the fuel starts to run the swelling, so the fuel starts to run the swelling, so the fuel starts to run out and then we had a big boom. So that out and then we had a big boom. So that out and then we had a big boom. So that was a a big noise here for um basically was a a big noise here for um basically was a a big noise here for um basically the supernova. This is a nice effect as the supernova. This is a nice effect as the supernova. This is a nice effect as well. And then like I said, we just kind well. And then like I said, we just kind well. And then like I said, we just kind of keep going through with this sort of of keep going through with this sort of of keep going through with this sort of feel up until the very end where we are feel up until the very end where we are feel up until the very end where we are just at us. So we have the word you just at us. So we have the word you just at us. So we have the word you pretty cool. So that is what one of the pretty cool. So that is what one of the pretty cool. So that is what one of the models decided to do. Let's take a look models decided to do. Let's take a look models decided to do. Let's take a look at the other one. We have Vesper archive at the other one. We have Vesper archive at the other one. We have Vesper archive and as we go down we have a similar sort and as we go down we have a similar sort and as we go down we have a similar sort of thing with sound. And it's kind of of thing with sound. And it's kind of of thing with sound. And it's kind of interesting because they had like a interesting because they had like a interesting because they had like a similar feel, right? like a 3D sort of similar feel, right? like a 3D sort of similar feel, right? like a 3D sort of background that's interactive with my background that's interactive with my background that's interactive with my mouse and it's telling some sort of mouse and it's telling some sort of mouse and it's telling some sort of story. It's telling some sort of story. It's telling some sort of story. It's telling some sort of journey, but they're both not bad. So journey, but they're both not bad. So journey, but they're both not bad. So far, I definitely think that the first far, I definitely think that the first far, I definitely think that the first one was a little bit had more of a wow one was a little bit had more of a wow one was a little bit had more of a wow factor for sure. It was a bit more factor for sure. It was a bit more factor for sure. It was a bit more immersive. This one tells a nice story immersive. This one tells a nice story immersive. This one tells a nice story and it still has some impressive and it still has some impressive and it still has some impressive features, but I think the first one so features, but I think the first one so features, but I think the first one so far was definitely on a different level.

  5. far was definitely on a different level. far was definitely on a different level. So, which one was Fable? Fable was the So, which one was Fable? Fable was the So, which one was Fable? Fable was the first one. So, once again, I think that first one. So, once again, I think that first one. So, once again, I think that Fable did a better job here. What you Fable did a better job here. What you Fable did a better job here. What you can see is Fable took 23 minutes whereas can see is Fable took 23 minutes whereas can see is Fable took 23 minutes whereas Soul took almost 7 minutes. And if we go Soul took almost 7 minutes. And if we go Soul took almost 7 minutes. And if we go down to the actual cost, Fable was 19 down to the actual cost, Fable was 19 down to the actual cost, Fable was 19 bucks 24 with 80,000 output tokens. And bucks 24 with 80,000 output tokens. And bucks 24 with 80,000 output tokens. And Soul was only a little over a dollar and Soul was only a little over a dollar and Soul was only a little over a dollar and output 20,000 tokens. So it's output 20,000 tokens. So it's output 20,000 tokens. So it's interesting like if we had Soul working interesting like if we had Soul working interesting like if we had Soul working enough to spend as much as Fable did, enough to spend as much as Fable did, enough to spend as much as Fable did, would Soul's output have been just as would Soul's output have been just as would Soul's output have been just as good, if not better? Maybe. soul is good, if not better? Maybe. soul is good, if not better? Maybe. soul is significantly cheaper on top of the fact significantly cheaper on top of the fact significantly cheaper on top of the fact that it typically spends less tokens in that it typically spends less tokens in that it typically spends less tokens in general just because of the harness and general just because of the harness and general just because of the harness and because of the way the model is trained because of the way the model is trained because of the way the model is trained I guess but yeah I mean this was almost I guess but yeah I mean this was almost I guess but yeah I mean this was almost 20 times cheaper for Fable but the 20 times cheaper for Fable but the 20 times cheaper for Fable but the question is is Fable's output was that question is is Fable's output was that question is is Fable's output was that 20 times better and I don't necessarily 20 times better and I don't necessarily 20 times better and I don't necessarily think that it was but just because we're think that it was but just because we're think that it was but just because we're going off of like the actual quality I'm going off of like the actual quality I'm going off of like the actual quality I'm going to say that I would have taken going to say that I would have taken going to say that I would have taken Fable's output in this one as well. All Fable's output in this one as well. All Fable's output in this one as well. All right so I did one more sideby-side right so I did one more sideby-side right so I did one more sideby-side experiment. This one's interesting. I experiment. This one's interesting. I experiment. This one's interesting. I gave it a different goal prompt and I gave it a different goal prompt and I gave it a different goal prompt and I said, "Design me five fundamentally said, "Design me five fundamentally said, "Design me five fundamentally different visual elements." They can be different visual elements." They can be different visual elements." They can be games, presentations, websites, games, presentations, websites, games, presentations, websites, simulations, whatever you want. I really simulations, whatever you want. I really simulations, whatever you want. I really wanted to see once again what does the wanted to see once again what does the wanted to see once again what does the model do with a super ambiguous prompt.

  6. model do with a super ambiguous prompt. model do with a super ambiguous prompt. So, let me open up the different outputs So, let me open up the different outputs So, let me open up the different outputs right here and we'll go ahead and right here and we'll go ahead and right here and we'll go ahead and compare. This time, I will go ahead and compare. This time, I will go ahead and compare. This time, I will go ahead and tell you which one is which as we're tell you which one is which as we're tell you which one is which as we're looking at them. All right, so this one looking at them. All right, so this one looking at them. All right, so this one is Fable and this one is Soul. So they is Fable and this one is Soul. So they is Fable and this one is Soul. So they each output one site and then we've got each output one site and then we've got each output one site and then we've got five different kind of like simulations five different kind of like simulations five different kind of like simulations or sister sites to go through. So let's or sister sites to go through. So let's or sister sites to go through. So let's just start with Fable and go through all just start with Fable and go through all just start with Fable and go through all of them and then we'll go to Soul. So of them and then we'll go to Soul. So of them and then we'll go to Soul. So this is what we got so far. The gallery this is what we got so far. The gallery this is what we got so far. The gallery five self-contained worlds. Let's look five self-contained worlds. Let's look five self-contained worlds. Let's look at Singularity. So I don't really know at Singularity. So I don't really know at Singularity. So I don't really know what's going on here. It says move to what's going on here. It says move to what's going on here. It says move to warp spaceime. Hold to feed it, I guess. warp spaceime. Hold to feed it, I guess. warp spaceime. Hold to feed it, I guess. And then you hit space to detonate. So And then you hit space to detonate. So And then you hit space to detonate. So if I hit space, we just blew something if I hit space, we just blew something if I hit space, we just blew something up, I guess. So, eh, I'm not really sure up, I guess. So, eh, I'm not really sure up, I guess. So, eh, I'm not really sure what they're going for here, but that's what they're going for here, but that's what they're going for here, but that's number one. We have second one, which is number one. We have second one, which is number one. We have second one, which is called Terra, where we kind of like have called Terra, where we kind of like have called Terra, where we kind of like have this flight simulator almost where we this flight simulator almost where we this flight simulator almost where we can steer with our mouse. We use W or S can steer with our mouse. We use W or S can steer with our mouse. We use W or S to speed up or speed down. We can go up to speed up or speed down. We can go up to speed up or speed down. We can go up or down. We can change the time of day. or down. We can change the time of day. or down. We can change the time of day. So, as far as like the physics on this, So, as far as like the physics on this, So, as far as like the physics on this, it's not too bad. Um, everything is kind it's not too bad. Um, everything is kind it's not too bad. Um, everything is kind of rendering in a bit strange. I'm not of rendering in a bit strange. I'm not of rendering in a bit strange. I'm not sure if they were doing that sure if they were doing that sure if they were doing that intentionally. Maybe that's like the intentionally. Maybe that's like the intentionally. Maybe that's like the vibe of this, but pretty cool, you know?

  7. vibe of this, but pretty cool, you know? vibe of this, but pretty cool, you know? Not too bad. I don't love it, but Not too bad. I don't love it, but Not too bad. I don't love it, but eh, I mean, for the fact that Fable just eh, I mean, for the fact that Fable just eh, I mean, for the fact that Fable just kind of wanted to do this and did it, kind of wanted to do this and did it, kind of wanted to do this and did it, it's all right. it's all right. it's all right. Okay, we've got Orbit, which is an Okay, we've got Orbit, which is an Okay, we've got Orbit, which is an arcade game. Two rings, one input. So, I arcade game. Two rings, one input. So, I arcade game. Two rings, one input. So, I think it looks like we just click to think it looks like we just click to think it looks like we just click to switch rings. We're trying to collect switch rings. We're trying to collect switch rings. We're trying to collect the coins. Okay, we're trying to avoid the coins. Okay, we're trying to avoid the coins. Okay, we're trying to avoid those things is what it looks like. Um, those things is what it looks like. Um, those things is what it looks like. Um, and that's how you get shattered. So, I and that's how you get shattered. So, I and that's how you get shattered. So, I mean, it plays fine. It feels very mean, it plays fine. It feels very mean, it plays fine. It feels very responsive. I'm not sure. This is a bit responsive. I'm not sure. This is a bit responsive. I'm not sure. This is a bit of a bug, though, huh? Um, the menu is of a bug, though, huh? Um, the menu is of a bug, though, huh? Um, the menu is like taking over me actually playing. like taking over me actually playing. like taking over me actually playing. So, I'm playing right now, but the menu So, I'm playing right now, but the menu So, I'm playing right now, but the menu isn't going away. So, that's a bit of a isn't going away. So, that's a bit of a isn't going away. So, that's a bit of a bug. Let's go ahead to number four. bug. Let's go ahead to number four. bug. Let's go ahead to number four. We've got inkflow. We've got inkflow. We've got inkflow. Um, click for new piece. I can change Um, click for new piece. I can change Um, click for new piece. I can change the pallet. I can save them as a PNG. I the pallet. I can save them as a PNG. I the pallet. I can save them as a PNG. I think this is just a weird like a board think this is just a weird like a board think this is just a weird like a board button sort of thing. I don't know if button sort of thing. I don't know if button sort of thing. I don't know if you guys ever did board button, but you guys ever did board button, but you guys ever did board button, but that's what this reminds me of, like that's what this reminds me of, like that's what this reminds me of, like just some very random thing. And the just some very random thing. And the just some very random thing. And the last one is the descent. So, scroll from last one is the descent. So, scroll from last one is the descent. So, scroll from sunlit surface to challenge. Okay, so sunlit surface to challenge. Okay, so sunlit surface to challenge. Okay, so this is kind of like a story again. It's this is kind of like a story again. It's this is kind of like a story again. It's like an interactive story um where we're like an interactive story um where we're like an interactive story um where we're actually going underwater. The actually going underwater. The actually going underwater. The background's changing. We're seeing background's changing. We're seeing background's changing. We're seeing different creatures go through deeper different creatures go through deeper different creatures go through deeper than the Titanic. Um this pressure, the than the Titanic. Um this pressure, the than the Titanic. Um this pressure, the sunlight, the temperature, all of that's sunlight, the temperature, all of that's sunlight, the temperature, all of that's changing. So, kind of just another changing. So, kind of just another changing. So, kind of just another little journey experience. So, that was little journey experience. So, that was little journey experience. So, that was Fable. I will say nothing overwhelmingly Fable. I will say nothing overwhelmingly Fable. I will say nothing overwhelmingly impressive there. Right. Let's go to impressive there. Right. Let's go to impressive there. Right. Let's go to soul, which already I think this looks soul, which already I think this looks soul, which already I think this looks better. This honestly kind of looks like better. This honestly kind of looks like better. This honestly kind of looks like a claw design sort of output. But

  8. a claw design sort of output. But a claw design sort of output. But anyways, impossible objects, five tiny anyways, impossible objects, five tiny anyways, impossible objects, five tiny worlds, no frameworks. The first one is worlds, no frameworks. The first one is worlds, no frameworks. The first one is Aurora Orchestra. So, Aurora Orchestra. So, Aurora Orchestra. So, I guess we're just kind of playing here I guess we're just kind of playing here I guess we're just kind of playing here with the northern lights. with the northern lights. with the northern lights. Yeah, not sure exactly what's happening, Yeah, not sure exactly what's happening, Yeah, not sure exactly what's happening, but we can change the voice. We can but we can change the voice. We can but we can change the voice. We can change the sky. We can hold for change the sky. We can hold for change the sky. We can hold for intensity. We've got other ones in here. intensity. We've got other ones in here. intensity. We've got other ones in here. So, we can change like the color of the So, we can change like the color of the So, we can change like the color of the northern lights, I suppose. Not sure northern lights, I suppose. Not sure northern lights, I suppose. Not sure what's going on here. That might be a what's going on here. That might be a what's going on here. That might be a bit of a bug. It seems like three and bit of a bug. It seems like three and bit of a bug. It seems like three and four don't actually work, but two and four don't actually work, but two and four don't actually work, but two and Oh, now two and one don't work at all Oh, now two and one don't work at all Oh, now two and one don't work at all either. Okay, so another little bug either. Okay, so another little bug either. Okay, so another little bug there. Let's go back to the gallery. there. Let's go back to the gallery. there. Let's go back to the gallery. Let's go to number two. Atlas of Lost Let's go to number two. Atlas of Lost Let's go to number two. Atlas of Lost Echoes. Echoes. Echoes. We've got a map. My cursor is showing We've got a map. My cursor is showing We've got a map. My cursor is showing where North is. What happens if I click where North is. What happens if I click where North is. What happens if I click on this Sleeping Sea? on this Sleeping Sea? on this Sleeping Sea? Okay. Um, Okay. Um, Okay. Um, I'm not really sure what we're doing I'm not really sure what we're doing I'm not really sure what we're doing here. In the bottom right, you can see here. In the bottom right, you can see here. In the bottom right, you can see it says echoes recovered. I guess I have it says echoes recovered. I guess I have it says echoes recovered. I guess I have to recover all five of these echoes. So, to recover all five of these echoes. So, to recover all five of these echoes. So, let's see if anything happens. let's see if anything happens. let's see if anything happens. Every place that misses us. Atlas Every place that misses us. Atlas Every place that misses us. Atlas complete. Keep exploring. Okay, so not complete. Keep exploring. Okay, so not complete. Keep exploring. Okay, so not really sure what that is. Let's go ahead really sure what that is. Let's go ahead really sure what that is. Let's go ahead and go to the next one. The glyph heist.

  9. and go to the next one. The glyph heist. and go to the next one. The glyph heist. So, the grid is hiding contraband words. So, the grid is hiding contraband words. So, the grid is hiding contraband words. Type every signal before the trace Type every signal before the trace Type every signal before the trace completes. Okay, so this is just like a completes. Okay, so this is just like a completes. Okay, so this is just like a typing game, I guess. Um, typing game, I guess. Um, typing game, I guess. Um, am I getting points? Oh, yeah. The am I getting points? Oh, yeah. The am I getting points? Oh, yeah. The points are in the top points are in the top points are in the top left. Whoa, that's not even a word. left. Whoa, that's not even a word. left. Whoa, that's not even a word. Okay, so this is just like a typing Okay, so this is just like a typing Okay, so this is just like a typing game, I guess. I don't really see much game, I guess. I don't really see much game, I guess. I don't really see much like feedback. I'm just kind of typing like feedback. I'm just kind of typing like feedback. I'm just kind of typing and those that's not a word either. I and those that's not a word either. I and those that's not a word either. I mean, I guess that's the point is it's mean, I guess that's the point is it's mean, I guess that's the point is it's trying to trip me up. Oops. Yeah, that's trying to trip me up. Oops. Yeah, that's trying to trip me up. Oops. Yeah, that's kind of the point, I guess. Okay. Eh, kind of the point, I guess. Okay. Eh, kind of the point, I guess. Okay. Eh, that's all right. Um, I mean, kind of a that's all right. Um, I mean, kind of a that's all right. Um, I mean, kind of a cool vibe, right? Like the actual cool vibe, right? Like the actual cool vibe, right? Like the actual aesthetics. I don't think you're losing aesthetics. I don't think you're losing aesthetics. I don't think you're losing lives, though. Like I don't know how lives, though. Like I don't know how lives, though. Like I don't know how this ever ends. this ever ends. this ever ends. Also, I already had a high score in Also, I already had a high score in Also, I already had a high score in here. here. here. So, definitely kind of buggy. Um, and So, definitely kind of buggy. Um, and So, definitely kind of buggy. Um, and let's go ahead and go to I guess we got let's go ahead and go to I guess we got let's go ahead and go to I guess we got two left. So, this one, this is just a two left. So, this one, this is just a two left. So, this one, this is just a slide deck. It looks like slide deck. It looks like slide deck. It looks like it looks like there are five slides. it looks like there are five slides. it looks like there are five slides. Not bad, though. I actually think that Not bad, though. I actually think that Not bad, though. I actually think that these are designed pretty well. This is these are designed pretty well. This is these are designed pretty well. This is interesting though, cuz this definitely interesting though, cuz this definitely interesting though, cuz this definitely looks like a claw design to me. Like, looks like a claw design to me. Like, looks like a claw design to me. Like, this definitely looks like something this definitely looks like something this definitely looks like something that that that Fable would whip up. I don't know why.

  10. Fable would whip up. I don't know why. Fable would whip up. I don't know why. the font and the color scheme just feels the font and the color scheme just feels the font and the color scheme just feels like a clawed thing. Anyways, the last like a clawed thing. Anyways, the last like a clawed thing. Anyways, the last one we got here is a tide pool. So, life one we got here is a tide pool. So, life one we got here is a tide pool. So, life is waiting. Touch the water to begin. is waiting. Touch the water to begin. is waiting. Touch the water to begin. Okay, I just dropped in a bunch of Okay, I just dropped in a bunch of Okay, I just dropped in a bunch of seeds. We've got a population of 320, seeds. We've got a population of 320, seeds. We've got a population of 320, diversity of two. I can give them diversity of two. I can give them diversity of two. I can give them sunlight. I can give them fresh rain. sunlight. I can give them fresh rain. sunlight. I can give them fresh rain. So, this is very much like a simulation. So, this is very much like a simulation. So, this is very much like a simulation. Um, this one already feels like it's Um, this one already feels like it's Um, this one already feels like it's like slowing down my computer. So, I like slowing down my computer. So, I like slowing down my computer. So, I don't know how much is going on back don't know how much is going on back don't know how much is going on back here, but not too bad. I like the ones here, but not too bad. I like the ones here, but not too bad. I like the ones that are simulations. I think they're that are simulations. I think they're that are simulations. I think they're kind of fun. kind of fun. kind of fun. So, yeah. Honestly, I don't even know So, yeah. Honestly, I don't even know So, yeah. Honestly, I don't even know what to say here. Like, I don't know what to say here. Like, I don't know what to say here. Like, I don't know which one to say I'm going to hand the which one to say I'm going to hand the which one to say I'm going to hand the crown to. I think I'm just going to go crown to. I think I'm just going to go crown to. I think I'm just going to go with Soul for this one because I think with Soul for this one because I think with Soul for this one because I think in general it had a bit of a better idea in general it had a bit of a better idea in general it had a bit of a better idea of like diversity and experience. The of like diversity and experience. The of like diversity and experience. The interesting thing here is when we take a interesting thing here is when we take a interesting thing here is when we take a look at the speed and the cost. So, I look at the speed and the cost. So, I look at the speed and the cost. So, I thought that this run would take the thought that this run would take the thought that this run would take the longest out of all of them because I was longest out of all of them because I was longest out of all of them because I was saying, "Hey, five very different saying, "Hey, five very different saying, "Hey, five very different things." I thought it would take maybe things." I thought it would take maybe things." I thought it would take maybe five times as long as the earlier ones, five times as long as the earlier ones, five times as long as the earlier ones, but this one was actually like the but this one was actually like the but this one was actually like the quickest on both fronts, which I thought quickest on both fronts, which I thought quickest on both fronts, which I thought was really interesting. This one took 15 was really interesting. This one took 15 was really interesting. This one took 15 minutes for Fable. And for Soul, this minutes for Fable. And for Soul, this minutes for Fable. And for Soul, this took 7 minutes, which I thought was took 7 minutes, which I thought was took 7 minutes, which I thought was really, really fast. And on the cost really, really fast. And on the cost really, really fast. And on the cost side, this costed Fable about 15 bucks side, this costed Fable about 15 bucks side, this costed Fable about 15 bucks with 65,000 output tokens. And on Soul, with 65,000 output tokens. And on Soul, with 65,000 output tokens. And on Soul, it took once again about a dollar and it took once again about a dollar and it took once again about a dollar and 22,000 output tokens. So very, very 22,000 output tokens. So very, very 22,000 output tokens. So very, very interesting to me. All right. So those interesting to me. All right. So those interesting to me. All right. So those agentic experiments with um cloud code agentic experiments with um cloud code agentic experiments with um cloud code and with codecs that was one thing and and with codecs that was one thing and and with codecs that was one thing and that's typically how I'm going to be that's typically how I'm going to be that's typically how I'm going to be actually driving these two models. So it actually driving these two models. So it actually driving these two models. So it was important for me to play around with was important for me to play around with was important for me to play around with stuff and of course all day I used it stuff and of course all day I used it stuff and of course all day I used it for just my general work but I also

  11. for just my general work but I also for just my general work but I also wanted to try just explicitly over the wanted to try just explicitly over the wanted to try just explicitly over the API just talking to the models and a lot API just talking to the models and a lot API just talking to the models and a lot of these were kind of like a oneshot hey of these were kind of like a oneshot hey of these were kind of like a oneshot hey what's this give me an answer what's what's this give me an answer what's what's this give me an answer what's this give me an answer rather than like this give me an answer rather than like this give me an answer rather than like an agentic loop with multi-step an agentic loop with multi-step an agentic loop with multi-step reasoning but I wanted to see what it reasoning but I wanted to see what it reasoning but I wanted to see what it looked like for you know speed and cost looked like for you know speed and cost looked like for you know speed and cost as well so the record here which is as well so the record here which is as well so the record here which is really interesting is that soul won 24 really interesting is that soul won 24 really interesting is that soul won 24 times and fable won three times there times and fable won three times there times and fable won three times there were also a lot of times when Fable were also a lot of times when Fable were also a lot of times when Fable refused to answer like literally just refused to answer like literally just refused to answer like literally just wouldn't submit an answer. It refused, wouldn't submit an answer. It refused, wouldn't submit an answer. It refused, which I thought was interesting because, which I thought was interesting because, which I thought was interesting because, you know, there's the security guard you know, there's the security guard you know, there's the security guard rails are baked in pretty hard. But rails are baked in pretty hard. But rails are baked in pretty hard. But also, look at the spend. I mean, Soul also, look at the spend. I mean, Soul also, look at the spend. I mean, Soul won 24 to3 for these kind of quick won 24 to3 for these kind of quick won 24 to3 for these kind of quick one-off tasks and Soul costed 16 bucks one-off tasks and Soul costed 16 bucks one-off tasks and Soul costed 16 bucks while Fable costed 63 bucks. But as far while Fable costed 63 bucks. But as far while Fable costed 63 bucks. But as far as like the actual capability, when as like the actual capability, when as like the actual capability, when Fable actually answered, it was pretty Fable actually answered, it was pretty Fable actually answered, it was pretty even. The reason why Soul dominated even. The reason why Soul dominated even. The reason why Soul dominated apparently is because Fable failed to apparently is because Fable failed to apparently is because Fable failed to answer a lot of the calls. But as you answer a lot of the calls. But as you answer a lot of the calls. But as you can see over here, score when answering. can see over here, score when answering. can see over here, score when answering. Soul had 0.98 and Fable had 966. So they Soul had 0.98 and Fable had 966. So they Soul had 0.98 and Fable had 966. So they are very similar models and I think it's are very similar models and I think it's are very similar models and I think it's just a perfect example of like the unit just a perfect example of like the unit just a perfect example of like the unit economics based on this task. Let's say economics based on this task. Let's say economics based on this task. Let's say the task is a five. Do you need a model the task is a five. Do you need a model the task is a five. Do you need a model that is a 10? Probably not. You only that is a 10? Probably not. You only that is a 10? Probably not. You only need a model that's maybe like a five or need a model that's maybe like a five or need a model that's maybe like a five or a six. So in this case with these quick a six. So in this case with these quick a six. So in this case with these quick oneshot, you know, API requests probably oneshot, you know, API requests probably oneshot, you know, API requests probably stateless. Soul seems to crush Fable stateless. Soul seems to crush Fable stateless. Soul seems to crush Fable here. And from an input output tokens here. And from an input output tokens here. And from an input output tokens perspective, Soul is basically half the perspective, Soul is basically half the perspective, Soul is basically half the cost of Fable. you know, half on the cost of Fable. you know, half on the cost of Fable. you know, half on the input and then a little over half on the input and then a little over half on the input and then a little over half on the output, but it's basically half. And if output, but it's basically half. And if output, but it's basically half. And if you compare Soul to like Opus 4.8, you compare Soul to like Opus 4.8, you compare Soul to like Opus 4.8, they're pretty much the same. Same on they're pretty much the same. Same on they're pretty much the same. Same on the input and then very similar on the the input and then very similar on the the input and then very similar on the output. So, that's pretty interesting to

  12. output. So, that's pretty interesting to output. So, that's pretty interesting to me. And it honestly feels like a better me. And it honestly feels like a better me. And it honestly feels like a better head-to-head comparison would have been head-to-head comparison would have been head-to-head comparison would have been Soul 5.6 versus Opus 4.8 rather than Soul 5.6 versus Opus 4.8 rather than Soul 5.6 versus Opus 4.8 rather than comparing Soul 5.6 and Fable 5. Like, I comparing Soul 5.6 and Fable 5. Like, I comparing Soul 5.6 and Fable 5. Like, I just think that they're not even on the just think that they're not even on the just think that they're not even on the same level as far as like a nextG model. same level as far as like a nextG model. same level as far as like a nextG model. Think about the fact that Fable jumps to Think about the fact that Fable jumps to Think about the fact that Fable jumps to a five. Soul, which is apparently their a five. Soul, which is apparently their a five. Soul, which is apparently their most capable model. Why would it not most capable model. Why would it not most capable model. Why would it not have been Soul 6? Like why are we 5.6? have been Soul 6? Like why are we 5.6? have been Soul 6? Like why are we 5.6? Doesn't a model that should be so so Doesn't a model that should be so so Doesn't a model that should be so so good deserve a full step up if there's, good deserve a full step up if there's, good deserve a full step up if there's, you know, fundamentally something so you know, fundamentally something so you know, fundamentally something so different that makes it like a really different that makes it like a really different that makes it like a really powerful scary model, but they decided powerful scary model, but they decided powerful scary model, but they decided to only bump it up to Soul 5.6, which to only bump it up to Soul 5.6, which to only bump it up to Soul 5.6, which makes me wonder like what are they makes me wonder like what are they makes me wonder like what are they cooking back there and what are they cooking back there and what are they cooking back there and what are they maybe waiting to drop as their next maybe waiting to drop as their next maybe waiting to drop as their next GBT6? Because I think that's when we GBT6? Because I think that's when we GBT6? Because I think that's when we have the nextG model that I truly think have the nextG model that I truly think have the nextG model that I truly think actually goes headto-head with Fable actually goes headto-head with Fable actually goes headto-head with Fable because right now I do not think that because right now I do not think that because right now I do not think that Soul does. I'll talk about that a little Soul does. I'll talk about that a little Soul does. I'll talk about that a little bit more once we get into the next bit more once we get into the next bit more once we get into the next section. But let's look at this. So section. But let's look at this. So section. But let's look at this. So score obviously soul won here but score score obviously soul won here but score score obviously soul won here but score when answered obviously it was much when answered obviously it was much when answered obviously it was much closer. So that's kind of like the closer. So that's kind of like the closer. So that's kind of like the reliability thing. Now on the cost side reliability thing. Now on the cost side reliability thing. Now on the cost side the API calls soul was much cheaper the API calls soul was much cheaper the API calls soul was much cheaper obviously 9 bucks to about 14 bucks. But obviously 9 bucks to about 14 bucks. But obviously 9 bucks to about 14 bucks. But then what's interesting is the gap here then what's interesting is the gap here then what's interesting is the gap here is not that big right the gap here is is not that big right the gap here is is not that big right the gap here is about five bucks. And if you think about five bucks. And if you think about five bucks. And if you think percentage-wise relative, it's even percentage-wise relative, it's even percentage-wise relative, it's even less, like a smaller percentage than how less, like a smaller percentage than how less, like a smaller percentage than how wide this gap is when we get to the wide this gap is when we get to the wide this gap is when we get to the actual agentic reasoning with Cloud Code actual agentic reasoning with Cloud Code actual agentic reasoning with Cloud Code as the harness and Codex as the harness, as the harness and Codex as the harness, as the harness and Codex as the harness, the gap in cost was just much much the gap in cost was just much much the gap in cost was just much much bigger, which is really interesting. And bigger, which is really interesting. And bigger, which is really interesting. And overall, Fable is much more expensive overall, Fable is much more expensive overall, Fable is much more expensive than Soul. And I think the token thing than Soul. And I think the token thing than Soul. And I think the token thing is just so interesting because let's say is just so interesting because let's say is just so interesting because let's say that Fable and Soul costed the exact that Fable and Soul costed the exact that Fable and Soul costed the exact same from an input and output token

  13. same from an input and output token same from an input and output token perspective. Soul would have still been perspective. Soul would have still been perspective. Soul would have still been meaningfully cheaper because it just was meaningfully cheaper because it just was meaningfully cheaper because it just was more efficient with tokens. I don't know more efficient with tokens. I don't know more efficient with tokens. I don't know exactly why that is, but it just seems exactly why that is, but it just seems exactly why that is, but it just seems to be so much more efficient with to be so much more efficient with to be so much more efficient with tokens. It's probably has a lot to do tokens. It's probably has a lot to do tokens. It's probably has a lot to do with codecs, too, because when I've done with codecs, too, because when I've done with codecs, too, because when I've done codecs and cloud code comparisons in the codecs and cloud code comparisons in the codecs and cloud code comparisons in the past, codeex has always been faster and past, codeex has always been faster and past, codeex has always been faster and more efficient with tokens. But anyways, more efficient with tokens. But anyways, more efficient with tokens. But anyways, just something I think is pretty just something I think is pretty just something I think is pretty interesting. This is also interesting on interesting. This is also interesting on interesting. This is also interesting on the speed side. So over API, the median the speed side. So over API, the median the speed side. So over API, the median API latency from Soul was quicker than API latency from Soul was quicker than API latency from Soul was quicker than Fable, but the mean, so the average was Fable, but the mean, so the average was Fable, but the mean, so the average was Fable being quicker. So that means like Fable being quicker. So that means like Fable being quicker. So that means like Soul is a little bit more all over the Soul is a little bit more all over the Soul is a little bit more all over the board. Some runs were super super long. board. Some runs were super super long. board. Some runs were super super long. Some runs might have been really really Some runs might have been really really Some runs might have been really really quick. Whereas Fable was more quick. Whereas Fable was more quick. Whereas Fable was more consistently just kind of hovering consistently just kind of hovering consistently just kind of hovering around like the 20 second mark. And around like the 20 second mark. And around like the 20 second mark. And that's why its median was still higher that's why its median was still higher that's why its median was still higher than Soul, but its mean was lower than than Soul, but its mean was lower than than Soul, but its mean was lower than Soul, which I just think is pretty Soul, which I just think is pretty Soul, which I just think is pretty interesting. But then when we see the interesting. But then when we see the interesting. But then when we see the Agentic builds, Fable was pretty much Agentic builds, Fable was pretty much Agentic builds, Fable was pretty much always going to be slower. So after always going to be slower. So after always going to be slower. So after running these different types of tests, running these different types of tests, running these different types of tests, some were fun, some were for design, some were fun, some were for design, some were fun, some were for design, some were, you know, just via API, and some were, you know, just via API, and some were, you know, just via API, and then of course my actual driving this on then of course my actual driving this on then of course my actual driving this on the day-to-day, here's where I landed.

  14. the day-to-day, here's where I landed. the day-to-day, here's where I landed. Overall, I feel like Fable is a better Overall, I feel like Fable is a better Overall, I feel like Fable is a better manager, and that's how I think of it. I manager, and that's how I think of it. I manager, and that's how I think of it. I think of it as a co-founder. I think of think of it as a co-founder. I think of think of it as a co-founder. I think of it as a manager. Soul is just a really, it as a manager. Soul is just a really, it as a manager. Soul is just a really, really good worker. Really good worker. really good worker. Really good worker. really good worker. Really good worker. Like I think that having Fable Like I think that having Fable Like I think that having Fable orchestrate a bunch of Soul agents would orchestrate a bunch of Soul agents would orchestrate a bunch of Soul agents would be amazing. I gave them each their other be amazing. I gave them each their other be amazing. I gave them each their other things that I would say like they are things that I would say like they are things that I would say like they are better than the other end. So, Solo is better than the other end. So, Solo is better than the other end. So, Solo is obviously better on price. It's much obviously better on price. It's much obviously better on price. It's much better on computer use. It's much better better on computer use. It's much better better on computer use. It's much better at playing devil's advocate because it at playing devil's advocate because it at playing devil's advocate because it feels like it's just a little more feels like it's just a little more feels like it's just a little more careful at finding the bugs and looking careful at finding the bugs and looking careful at finding the bugs and looking at things from different angles. I also at things from different angles. I also at things from different angles. I also gave it the verification because of the gave it the verification because of the gave it the verification because of the computer use and because of this whole computer use and because of this whole computer use and because of this whole devil's advocate and just like really devil's advocate and just like really devil's advocate and just like really being careful and really thinking about being careful and really thinking about being careful and really thinking about what did they say, what did the user what did they say, what did the user what did they say, what did the user tell me to do and what am I going to do tell me to do and what am I going to do tell me to do and what am I going to do and I'm going to do exactly that. and I'm going to do exactly that. and I'm going to do exactly that. Whereas sometimes Fable's a bit more Whereas sometimes Fable's a bit more Whereas sometimes Fable's a bit more like it'll push back a little bit more like it'll push back a little bit more like it'll push back a little bit more and it's almost like sometimes sassier, and it's almost like sometimes sassier, and it's almost like sometimes sassier, you know, like sometimes it's not just you know, like sometimes it's not just you know, like sometimes it's not just like I want to take a request and action like I want to take a request and action like I want to take a request and action it. I want to push back and be like a it. I want to push back and be like a it. I want to push back and be like a consultant here, which is good thing, consultant here, which is good thing, consultant here, which is good thing, right? That's why I said it's a manager. right? That's why I said it's a manager. right? That's why I said it's a manager. There's pros and cons to that. And then There's pros and cons to that. And then There's pros and cons to that. And then of course, I gave Soul the speed. Now, of course, I gave Soul the speed. Now, of course, I gave Soul the speed. Now, Fable, I said it's just much more Fable, I said it's just much more Fable, I said it's just much more creative. It feels more creative. It creative. It feels more creative. It creative. It feels more creative. It feels like it's better at writing. It feels like it's better at writing. It feels like it's better at writing. It feels like it's better at brainstorming.

  15. feels like it's better at brainstorming. feels like it's better at brainstorming. It feels like it's better at advising. It feels like it's better at advising. It feels like it's better at advising. It's really strategic. The knowledge It's really strategic. The knowledge It's really strategic. The knowledge work all day. I still prefer Fable, but work all day. I still prefer Fable, but work all day. I still prefer Fable, but you know, it's just not the the cost. I you know, it's just not the the cost. I you know, it's just not the the cost. I can't always justify it. It felt like it can't always justify it. It felt like it can't always justify it. It felt like it was better at making videos. If you saw, was better at making videos. If you saw, was better at making videos. If you saw, I made two videos recently on YouTube. I made two videos recently on YouTube. I made two videos recently on YouTube. One was called like Fable 5 made this One was called like Fable 5 made this One was called like Fable 5 made this entire video, and the other one I just entire video, and the other one I just entire video, and the other one I just dropped earlier today, which was called dropped earlier today, which was called dropped earlier today, which was called Soul made this entire video. So, go Soul made this entire video. So, go Soul made this entire video. So, go watch both of those. They each created watch both of those. They each created watch both of those. They each created YouTube videos for me completely from YouTube videos for me completely from YouTube videos for me completely from scratch. And just see which one you scratch. And just see which one you scratch. And just see which one you thought was better. I liked Fables thought was better. I liked Fables thought was better. I liked Fables better. I also said that Fable is better better. I also said that Fable is better better. I also said that Fable is better at not overengineering because Soul runs at not overengineering because Soul runs at not overengineering because Soul runs so many tests, which also is interesting so many tests, which also is interesting so many tests, which also is interesting when you think about the token thing, when you think about the token thing, when you think about the token thing, right? Like how can it be so efficient right? Like how can it be so efficient right? Like how can it be so efficient with tokens if it writes so many tests with tokens if it writes so many tests with tokens if it writes so many tests and sometimes it will overthink, and sometimes it will overthink, and sometimes it will overthink, especially when I had Solon Ultra, it especially when I had Solon Ultra, it especially when I had Solon Ultra, it was just going and going and going and was just going and going and going and was just going and going and going and going, which, you know, sometimes good, going, which, you know, sometimes good, going, which, you know, sometimes good, sometimes bad. There's always pros and sometimes bad. There's always pros and sometimes bad. There's always pros and cons, but just pure capability. I mean, cons, but just pure capability. I mean, cons, but just pure capability. I mean, you can't even argue. Fable 5 is in you can't even argue. Fable 5 is in you can't even argue. Fable 5 is in another tier. It's just on another another tier. It's just on another another tier. It's just on another level. And Soul is really good. I think level. And Soul is really good. I think level. And Soul is really good. I think it's more comparable to Opus 4.8. It's it's more comparable to Opus 4.8. It's it's more comparable to Opus 4.8. It's definitely better than GBT 5.5, but it definitely better than GBT 5.5, but it definitely better than GBT 5.5, but it just it's not a Fable 5. And honestly, I just it's not a Fable 5. And honestly, I just it's not a Fable 5. And honestly, I think if it was Fable 5 tier, it would think if it was Fable 5 tier, it would think if it was Fable 5 tier, it would be charged at Fable 5 tier. Like, it be charged at Fable 5 tier. Like, it be charged at Fable 5 tier. Like, it would be priced that high. And it's not.

  16. would be priced that high. And it's not. would be priced that high. And it's not. It's priced like Opus. So, overall, what It's priced like Opus. So, overall, what It's priced like Opus. So, overall, what I'd say is Fable is good for my I'd say is Fable is good for my I'd say is Fable is good for my reasoning and my judging. And then Soul reasoning and my judging. And then Soul reasoning and my judging. And then Soul is just a shipping and executing AI is just a shipping and executing AI is just a shipping and executing AI model. And just so we kind of like put model. And just so we kind of like put model. And just so we kind of like put it into perspective, I kind of tried to it into perspective, I kind of tried to it into perspective, I kind of tried to like map out where I think that these like map out where I think that these like map out where I think that these top four models that, you know, we're top four models that, you know, we're top four models that, you know, we're talking about right now sit. I've got talking about right now sit. I've got talking about right now sit. I've got GBT 5.5 and Opus just very very similar. GBT 5.5 and Opus just very very similar. GBT 5.5 and Opus just very very similar. I would say because I drive most of my I would say because I drive most of my I would say because I drive most of my work with Opus, I would put GBT 5.5 just work with Opus, I would put GBT 5.5 just work with Opus, I would put GBT 5.5 just like a little bit behind. Soul is like a little bit behind. Soul is like a little bit behind. Soul is definitely in front of both of these. definitely in front of both of these. definitely in front of both of these. Like that's very clear. It's a very very Like that's very clear. It's a very very Like that's very clear. It's a very very good model, but I still think there's a good model, but I still think there's a good model, but I still think there's a pretty large gap right here between, you pretty large gap right here between, you pretty large gap right here between, you know, Soul actually being to be on know, Soul actually being to be on know, Soul actually being to be on Fable's level. Like there is still a Fable's level. Like there is still a Fable's level. Like there is still a pretty big gap here. So, that's the way pretty big gap here. So, that's the way pretty big gap here. So, that's the way I feel about it. Hopefully, all of this I feel about it. Hopefully, all of this I feel about it. Hopefully, all of this makes sense to you guys. Like I said, makes sense to you guys. Like I said, makes sense to you guys. Like I said, it's definitely one thing to look at the it's definitely one thing to look at the it's definitely one thing to look at the benchmarks, but really what you have to benchmarks, but really what you have to benchmarks, but really what you have to do is you have to get your hands dirty. do is you have to get your hands dirty. do is you have to get your hands dirty. You have to do actual work that you do You have to do actual work that you do You have to do actual work that you do on your day-to-day. And it's a feel on your day-to-day. And it's a feel on your day-to-day. And it's a feel thing because some people will probably thing because some people will probably thing because some people will probably come out the gate and say, "Soul is come out the gate and say, "Soul is come out the gate and say, "Soul is better than Fable, hands down." And some better than Fable, hands down." And some better than Fable, hands down." And some people will not agree with that at all. people will not agree with that at all. people will not agree with that at all. It's all about your use case and your It's all about your use case and your It's all about your use case and your feel and the way that you instruct it feel and the way that you instruct it feel and the way that you instruct it and the way that you've got your harness and the way that you've got your harness and the way that you've got your harness and your skill set up. So, everyone's a and your skill set up. So, everyone's a and your skill set up. So, everyone's a little different, but that is kind of my little different, but that is kind of my little different, but that is kind of my opinions after playing around with this opinions after playing around with this opinions after playing around with this model all day long. But as always, if model all day long. But as always, if model all day long. But as always, if you guys enjoyed the video or you you guys enjoyed the video or you you guys enjoyed the video or you learned something new, please give it a learned something new, please give it a learned something new, please give it a like. Helps me out a ton. And as always, like. Helps me out a ton. And as always, like. Helps me out a ton. And as always, I appreciate you guys making it to the I appreciate you guys making it to the I appreciate you guys making it to the end of the video. I'll see you on the end of the video. I'll see you on the end of the video. I'll see you on the next one.

Summary

The main theme is comparing the performance and cost of GBT 5.6 Soul against Fable 5, specifically for developing browser-based games. The speaker tested both models with the same prompt, asking them to create a playable open-world bike game, and will discuss the pros, cons, and their personal preference for practical use cases.

View original episode ↗