Anthropic Outages Vs Morpheus Marketplace | Everclaw No More
1 hr 2 minAudio
Zion, hear me! For Season 2 of the Mere Morpheus podcast I'm going to be uploading the Morpheus builder weekly updates. My reason for doing this is to make it more accessible for those who want an update directly via their podcast app and to have them all in one place. If you'd like to participate they are held weekly on the @MorpheusAIs Twitter spaces. So enjoy Episode #69! Recorded: 16 April 2026 AI SUMMARY: This episode discusses the reliability crisis in centralized AI highlighting Anthropic's 129 outages in 90 days. It argues decentralized inference via Morpheus' marketplace provides essential uptime and permissionless access. The conversation notes open‑source models like GLM‑5.1 are now "good enough" for serious coding when used with agentic workflows and cross‑model audits. Practical updates include the rebrand of Everclaw to the Morpheus Skill for simpler decentralized inference and a comparison of memory systems. The episode concludes that Morpheus' open marketplace aligns price privacy and reliability sustainably. Timeline: (00:00:00) Intro (00:00:22) Claude outages and the case for zero‑downtime networks (00:04:33) Why redundancy and permissionless access matter (00:07:48) Opus 4.7 hot takes: marketing bump or real gains? (00:11:18) GLM 5.1 impresses: open source coding results (00:16:42) Is Anthropic prepping for IPO? Pricing, caps, and ads risk (00:19:08) Community call‑ins: market moats and PR narratives (00:21:36) ID requirements, data hoovering, and hostile UX (00:26:29) Guest intro: Micah Winklespeck on heavy Claude usage (00:31:11) From one‑shot to engineered processes: agent harnesses (00:36:09) Memory matters: configuring, retrieving, and context tools (00:40:50) ChromaDB vs Neo4j: fit‑for‑purpose memory backends (00:43:41) Hermes vs OpenClaw: continuity and user experience (00:45:14) Everclaw rebrands to Morpheus Skill: agent‑agnostic access (00:50:00) Under the hood: how the Morpheus inference marketplace works (00:54:41) Pricing, demand, and near‑term arbitrage dynamics (00:59:48) Next steps and trials: joining and giving feedback If you would like to support me for the value I provide you can use the referral link below when depositing capital and we will both earn bonus MOR. Alternatively you could send me a token of appreciation directly to my wallet ;) Referral Link: https://dashboard.mor.org/capital?referrer=0xE935f231c99c04Ee0b4532a3d0BdA81B152a0384 Wallet Address: 0xE935f231c99c04Ee0b4532a3d0BdA81B152a0384 Connect with Mere Mortals: Website: https://www.meremortalspodcasts.com/ Discord: https://discord.gg/dX9BEhT3kz Twitter/X: https://twitter.com/meremortalspods Instagram: https://www.instagram.com/meremortalspodcasts/ TikTok: https://www.tiktok.com/@meremortalspodcasts Value 4 Value Support: Website: https://www.meremortalspodcasts.com/support Paypal: https://www.paypal.com/paypalme/meremortalspodcast
Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.
Transcript
From the show. Tap a time to play from there.
David JohnstonIt's been a hell of a week for open source, for announcements, for developments in the space. Like, if you guys haven't been paying attention, it's basically something new every single day. So, Bo, where do you wanna where do you wanna start, man? There's all there's all these new models. We can talk about that. There's all the drama with Anthropic. We can get into that a gonna say, I I think the best place to start is
Bowen Belmerdown goes Claude again. So yesterday, obviously, there was a a really large outage with Claude affecting tons and tons of people I know. I was testing it for a while to see how long it took to get back up. And so it prompted me to take a look at, you know, the number of reported outages. So in the last ninety days alone, according to isdown.app, which is obviously the authority of if something is down or not, They have had a 129
reported incidents with Claude over the last ninety days, with 41 of them being considered major outages in entire regions of the world, and a median resolution time of one hour and six minutes, which, you know, for all the talk we do of of data privacy and, like, access to intelligence, which are, of course, like, key tenants of what Morpheus and decentralized AI provides us with, something we don't always focus as much on and probably should, and this kinda brings it to the forefront, is is the ability to have a network with no downtime because you're not reliant
on a central server anywhere.
David JohnstonYeah. I mean, we should also say they were not only down yesterday, they were down Monday, and they were down Sunday, and they had downages on Friday and Saturday. I think I looked back at their status bar. And in the last thirty days, they've had a major disruption of service, 18 out of thirty days. So, you know, it it's a bit ironic where, you know, they're sort of going out there with their new model and say, look. Ours ours model is so amazing. It found all these zero days and, you know, these other pieces of software. It's like, dude, you can't even keep your own system online.
It's like, what what are you talking about? And so if you're gonna build anything serious in AI, like, 18 disruptions in thirty days is completely unacceptable for anybody building a serious product. I mean, if you go to most industries, they want three nines, meaning 99.9% uptime. Anthropic has one nine right now. They're 98
uptime. Right? And so, like, that's not even close to good enough to build serious products. And so to your point, Bo, it's not just cheaper. It's not just private. Morpheus can give you a system that won't go offline all the time because you have different providers. You can switch models. You can, you know, have transparency into how they're working. You don't have this black box that just randomly turns off or becomes dumber. That's the other thing we should talk about. Like, the benchmarks are pretty crazy. People have recorded
4.6 has gotten something like 40% dumber the last two weeks. For whatever reason, they've been cutting back on the thinking and, you know, they're not only making it more expensive, but, like, they're degrading their performance.
Bowen BelmerLike, how do you build on that? Absolutely. I I wanna linger. I do wanna talk benchmarks, but I because that actually ties nicely into another topic I wanna make sure we cover today. But before we get to that, I do wanna linger on the downtime piece because to your point, I mean, it's again, like, we obviously make the Bitcoin analogy often or something like Ethereum. We if you're relying on your agent to execute important tasks for you, which is of course the goal of this. Right? It's like you wanted to actually be able to do useful things that are ultimately important,
whether the you in question is literally you as an individual, or like an entity that you represent, or even maybe a nation state. You don't just need a system that won't go down because they're good. You need a system that theoretically really can't because it has redundancy, and and no one can stop you from accessing it. So for example, I mean, if if one technically speaking, if one laptop somewhere on Earth is running Bitcoin, Bitcoin survives. All of it.
Or whatever. A full node. Right? Granted, that would be maybe hard on a laptop today. But the point persists that that is the type of system that we ultimately wanna build towards. And even if so if we look at just the private enterprise component, why would you wanna even take the risk? Like, let's say, okay, let's say Anthropic did have, you know, three nines. Let's say they got to 99.9% uptime, under regular conditions. They have the ability to give you specifically not that, and the other parties who they want to have that can have that, which also poses a problem. What if you're doing some type of, you know, unfortunately,
my brain, like, exclusively works in finance terms. But the first thing I think of is if you're, you know, a fund trading against another fund and I'm using AI as a tool, but the other fund can pay them more money to have better access to data than I can, I'm at a perpetual disadvantage. Or if they can even shut me down for ten seconds, that's a problem. You know? And, like, now apply that to health care. Apply that to any plethora of things. Like, it's a huge issue. And the last point that I like to make, and I used to bring this up all the time. I feel like I haven't talked about it in a while, is
I personally believe that Morpheus is a national security tool. I think that the government and the government agencies should really take a look at things like what we're building and consider incorporating it when they're building their AI stack because it's not you don't have a central point of failure. Like, if someone's trying to attack your network, well, where are they gonna attack? There's no physical specific location to even go after.
David JohnstonYeah. Well, I mean, it sort of harkens back to the early days of the Internet. Right? ARPANET, you know, exists because, you know, they wanted to create a network that would be robust in case of a a big war. You know, any one particular city, you know, was bombed or or fell, it wouldn't bring down the whole network. Right? And that ended up, you know, starting to become the the backbone of the modern Internet, and eventually it was everywhere. And so, yeah, like, there's no CEO of the Internet. There's also, you know, not a lot of centralized risk. Right? I mean, you could name out some of the providers like Cloudflare,
AWS, but they're they're running one piece. Right? One set of data centers, one set of nodes. But because you can switch to anybody else, it's it's really antifragile. So, yeah, it's it's worth making the point that AI should be similarly antifragile. It shouldn't rely on one or two big players, and they have a hiccup or a bug or a leak, and all of a sudden, everybody's stuff goes down. So yeah. No. It's it's it's like Anthropic has just been gifting us users every day. Yeah. I know. And again. Right? Well, this is where I knew that
Bowen Belmerone advantage that decentralized AI has over something like DeFi and something like Bitcoin did is the systems are being built in parallel with one another, whereas, like, DeFi and Bitcoin was kind of looking to jump into and replace preexisting systems. Now we're getting to see what it looks like when it's built in parallel. So every time something like this happens, more and more people awaken to the fact that, oh, this is bad. There's a solution for this. And, you know, ultimately, of course, we we believe that that's Morpheus.
David JohnstonYeah. A 100%. So what should we get into first? There's talk of 4.7, but, you know, my hot take is Opus 4.7. Honestly, it just kinda feels like they degraded the performance of Opus 4.6 so much that then they just gave back the existing model with, you know, slight improvements and a new number. Right? So somebody was doing some analysis in it, and it looks like they did something similar when they did the launch of 4.5. I don't know if they're, like, trying to make the model look better or like give people this experience like the old model doesn't work and so they better shift to the new model.
Because apparently, they've enabled more thinking. They want you to burn more tokens and it's sort of like if your experience the last week was, oh, this thing isn't working. Oh, thank goodness they released a new model and this one works. It kinda feels like this bait and switch that they're doing for marketing purposes. I mean, that or they're just incompetent and and can't keep it online at the same level of of performance, but, you know, I I tend to feel like it it might be marketing. I'd love to hear,
Bowen BelmerKyle and, Tomas's stances on this because I I think it's too normy of a user to be as impacted by some of this stuff as some of you guys are that are, like, more deep in code.
Kyle (Bow Tied Blue Fin)Yeah. Definitely. So I'll come out first and say that I was wrong last week. Last week, I came out and said that we think Opus four six is dumber because they changed just our thinking settings. But after going in and manually adjusting my thinking settings, it was still dumb. So, David, I think you were spot on that Anthropic must have been doing some
monetization, decreases, or some sort of limiting over the last two weeks because I think, fundamentally, the performance has dropped. They also have had a lot of issues on keeping it live. So I assume that's something with splitting their GPUs to try and deploy four seven, while also running, four six and and having problems. So, I think it's probably a mix of those things.
I have not tried four seven yet, but from some of the early feedback I've seen, yeah, it it looks like some incremental improvements. It probably looks like cranking that quantization back up to where four six was originally. But, I think the biggest takeaway from the new claw launch is their tokenization and that, the same amount of output is now resulting in, higher token counts and higher charging. So it's pretty much I I sent a a meme to someone earlier. It's like,
the trade offer meme of you get slight improvement, we get 35 to 50% more revenue. And I think that every single time this happens, people are going to get more and more pissed off about their monthly token costs on Anthropic and and consider the open source alternatives, which, you know, really are getting closer and closer and closer to that to that frontier model intelligence benchmark. So I just started using GLM 5.1 like you have, David, and and I've had
really, really great results coding so far. Unexpectedly
David Johnstongreat results, to be honest. Yeah. No. I've been impressed. And it's helpful, Bo, to understand something that, you know, people see these benchmarks. A lot of them are what's called like one shot. You know, basically, you asked it to do something and didn't get it right the first time. That increasingly doesn't matter. Right? How these models work these days is the model does an output. Okay. It tried to make the website.
Let's say it got 60% of the way there. Okay. Well it's gonna look at its output the next ten seconds and say, oh, well, I I didn't get this part done. I'm gonna go ahead and fix that. Okay. Now it's 75% done. It's gonna it's gonna do another turn. It's gonna do another cycle in the next ten seconds and say, oh, okay. Let me fix this, this, and this. It fixes the last three things. Maybe it's 95% of the way there. Great. It did it once more, now it's on its fifth or sixth shot, and it's a 100% perfect. Right? I don't need and maybe that whole process took a couple of minutes. Let's tape it say that even took five or ten minutes. Like, I didn't need it to work perfectly
in five seconds. Right? It took me longer than five seconds to come up with the idea for the website I wanted to call it to build. Right? So we're crossing this chasm, like Kyle is saying, where once the open source and I think 5.1 is it. It's good enough that it pretty much works. And if it has an error, it's gonna go back and do another cycle and fix the error. Right? And I don't think people are that sensitive to whether it took, you know, two minutes or four minutes to get a perfect result. Like, I'm gonna go grab a coffee and I'll come back and it'll be done. Right? And why would I pay 10 x as much,
right, to to get it done, you know, you know, slightly faster? Right? So we're kind of crossing this chasm where where if it's good enough, okay, it'll take a couple extra cycles, but it'll get the same thing done at basically the same quality. That's been my experience with with five point one. So I'm I'm happy to say I can officially say now I've cut the cord. I haven't used Quad I think in probably almost a week. Almost a week since we last talked. I don't think I've used it since Friday or Saturday
Bowen Belmerlast week. Well to be fair, there was only about fifteen minutes of uptime that you could have been using it.
David JohnstonWell and that was the forcing function. A bunch of people flooded into my DMs and they're like, my claw doesn't work. I can't, you know, do all of my, you know, normal work tasks. How about that Morpheus thing? Like, how do I get that? And I couldn't I can't tell you how many people I gave app.more.org. Right? And they're like, okay. How do I get more? How do I stake it? Oh, you know, go here or download this skill. You know? And twenty minutes later, they're like, okay. Great. I'm all set up. I'm switched over. I'm I'm set. And and they've got all their agents stakes. So it's it's really cool, you know, the the hard work that Kyle and Alan and Thomas and everybody else did to get
the API and the whole process smooth is, like, just starting to pay off. And so that's that's really rewarding.
Bowen BelmerIt is. Well, and the other thing too, I was just thinking as you were talking, the example you gave was you're specifically you're specifically prompting, and then waiting for a response. But if it's like a recurring task anyway, you won't even know necessarily that it took slightly longer than it maybe otherwise would have.
David JohnstonYeah. If it's gonna run a cron job at, you know, 2PM on a Tuesday,
Thomas Borrelyou know, okay. It took an extra thirty seconds in the back end. You know? Yeah. You wouldn't necessarily see it. Yeah. Exactly. Sorry, Thomas. Did you have something? No. I was just gonna say, I think what what matters most isn't so much the one shot as it is the number of interactions interactions that you have to have as the whatever you want built gets built. Right? So if I describe what I want, and then it takes another two minutes or five minutes or whatever, right, because there's more tools being called, which could lead to a better output.
As long as it doesn't come back and say, hey, can I do this? Hey, can I do that? Which Claude is increasingly doing now. And I don't know if that's one way for them to sort of better organize the queues of users that are using their system. But if you can just let it run, and it doesn't interact with you, and to the point, you know, David made, where it works its own iterations, then you have something that functions a lot closer to the way the human brain works. Right? Like, you don't write a novel one shot. You start it, and you read it,
you think of things you could improve, and you go and iterate on it. And that's how you get that that output that you like and and you're happy with.
David JohnstonYeah. That's a good point. It's it's about, like, does it get done what you wanna get done without, you know, having to come back and, you know, sort of redo the work and, you know, have you explain it and do a bunch of interactions.
Thomas BorrelYeah. And, you know, just just to go back on on the points that we made earlier on Anthropic, I wonder how much of what we're seeing right now has to do with them prepping for the IPO. Because I mean it's clear that the usage, whether you're on a pro plan or a max plan, is significantly subsidized. You burn way more than $200 worth of tokens when you're on the max plan.
How much effort are they putting in right now to tighten that up so that the pitch deck doesn't show a big gaping hole on the bottom line. And they start showing progress, right, in terms of them reducing that incentive that they're putting in front of everyone with the pro plan and the max plan. Just that trend is going to have to continue, right? At some point they're going to have to start generating
revenue, which I cannot believe they would at $20 a month on a pro plan or $200 a month on a max plan.
David JohnstonYeah, well that's the other thing is if they're gonna get to go public, all of a sudden the market's gonna you know, are you making a profit or, you know, are you just lighting a lot of money on fire to get market share? Right? And, you know, that works for a while, and and then eventually the market wants you to be to be profitable.
Thomas BorrelRight? Yeah. And and that's when the ancient vacation begins. Right? So now you start getting ads and and all of this. So I think making the switch now to open source models is the right move to make because you're approaching that parity, and you're not being essentially sucked into that trend of we gotta we gotta make we gotta make a profit, and because of that, we're gonna start we're gonna start using
more data that you're sending to us than we already than we already are or pulling an OpenAI and pushing ads into into the the output. Yeah.
David Johnston100%.
Bowen BelmerHey. I see Ken's. Hey, Ken. I see you you have your hand up. Would love to hear hear from you.
Kyle (Bow Tied Blue Fin)Hey, everybody. Hey.
Ken DiCrossSo I was just, you know, catching the news this morning as well and hearing you guys talk, like, couple comments. It feels like I saw, like, remember in, like, 2023, 2024, we were talking about how they were never gonna give us the best model, the the centralized options. Like, they were never gonna do that. It was always gonna turn into the iPhone where oh, that's what I initially thought where it's like, they'll give you a little bit better camera, a little bit better battery life, and they'll they'll just iPhone this so that they have
they can just continue to squeeze profit out for the next 15 generations. David, what I wasn't anticipating is them pull up a page from, like, the the job numbers, the job number data where they they push out a big number, and then they they start, like, retracting, you know, later. Like, they they start dialing back the capability. Like, oh, that's that's it's a that's I didn't I didn't even think that they were gonna do that. So it's, like, good on them for getting that creative.
David JohnstonYeah. What was what was it? Apple got caught basically engineering obsolescence where at three years exactly, the the phone battery would die on purpose. They got they got caught, you know, red handed and lost a big lawsuit over that. But No. I mean, that's what they're always gonna do. Right? Their their goal is to extract as much value as possible, and and that's kinda where they're at because I don't think they have a defendable moat. Right? The open source models have caught up. Right? And so they're gonna try to,
you know they're they're back with the scare tactics. Right? Like, oh, our model is so powerful. We can't possibly release it. It would do all these cybersecurity things and, you know, we've we've only let a privileged few, you know, handle it right now and, you know, access it. But, you know, I mean, I think a lot of that, again, is is marketing.
Bowen BelmerYeah. I would think so. And and if if they are gonna IPO too, I mean, it's a race to IPO between them and SpaceX who now wholly owns x AI. So Yeah. They need to, like, extract every single cent of value that they can and and either beat them to market or try to spook some type of some type of moat that may or may not be real.
David JohnstonYeah. Exactly. But, no, I think the timing, like you said, is is great. You know? Ken, that stuff we were talking about in 2023, 2024, like, it's reality now. Agents are mainstream. People are using this in their daily workflows. They depend on these tools. And between introducing government ID, now required for for anthropic subscriptions apparently, they are using and hoovering up all your data, the introduction of ads, racking up the cost, banning users
that use a tool like OpenClaw that they don't like. I mean, like, this has become really sort of a hostile relationship with with their user base. Right? And, yeah, it's it's good that we've got Morpheus and, you know, it as an alternative because I can't imagine if three years ago Morpheus hadn't come along and and built all this out, we'd be in a really bad spot. Like, what's your real alternative if you didn't have open source inference and open source agents? Right? You'd just be, you know, going between one corporate stack or another. So, you know, it feels like what we what we built is is definitely sorely needed and has come and matured just at the right time for people to have an option.
Ken DiCrossYeah. I don't know if Bo or Thomas said it because I had my phone down when I was listening. But when you're talking about the subsidization of of, like, the pro versus the normal, subscriptions, that's that was my moment, like, a couple weeks ago, and I've been, like, stacking Morpheus. Because, like, it's already expensive, you know, to use their products and they're subsidizing. Like, wait till they don't subsidize anymore.
Like, what the what the cost is gonna be. Yeah.
Thomas Borrel100%. 100%. I mean, if you look at, you know, just the cost of renting GPUs and how many GPUs you need to run one of those models, the math just don't work. They work at $25 a million token, but then, okay, well let's say that's the price. That means you're burning, what is it, 8,000,000 tokens on a max plan? Like, what? No. You do that in half an hour.
So they have to subsidize you.
David JohnstonWell, I see we've got Misha on the call as well. Maybe we can get him promoted. I know he's one of the folks that Anthropic was clamping down on and made the the switch recently, so I'd love to get him up here. If you wanna talk about that experience, you know, that's it's it's definitely something we're seeing all over the place. So, you know, the the market's really trying to starting to respond.
Kyle (Bow Tied Blue Fin)Yep. While while we get him up there, just as far as how much are people going to spend on on Anthropic when that switch is over. I think we're probably a couple weeks away from really finding out after they shut down the OAuth connection within OpenClaw. And if you wanted to continue using it, you have to use the, you know, the the metered usage essentially or pay as you go. So I think when those bills become due from everyone who who has been running it in that manner,
we will, we'll we'll start to see exactly how much that cost and and get some of that outreach. But excited to hear from Mika or Micah, David.
David JohnstonYeah. I'm gonna add him right right now. Send invite. Cool. Yeah. He said he's working on getting up there. So, yeah, I mean, that's that's I think the the big story. So we saw and and just to go back to the government ID stuff, you know, I can't say how onerous this is. Right? I mean, introducing KYC to use an AI is crazy. You know, this is this is should be an open informational tool. Imagine you needed, you know, your your driver's license to get an email account, right, or your driver's license to, you know, use use the Internet or go to a website or or go to Google,
you know, it or, you know, it's it's very it's very draconian. And what it does is it means they're gonna block large parts of the world. Like, oh, we don't want users, you know, from Africa, you know. Oh, we maybe they they they burn too many tokens and they, you know, can't pay enough for the subscription or they've got some policy that's blocking a part of the world, you know, Latin America or Africa or something, like, they could just turn off access. Oh, I'm sorry. You don't have a DMV, you know, license from from New York or or Texas. Get out of here. So, you know, I I I think think the introduction of that stuff is just gonna push more and more people to the open source option. But, Misha, see I see you're up here, man. Good to see you, bro. Hey, guys. I'm Micah Winkle Speck, and been
Micah Winkelspechtin the blockchain crypto, primarily Bitcoin movement since 2013. So I ran a company called Gem and sold it to a company called BlockDaemon. And now I've been spending all my time going back to my roots and writing writing code. And I've been a heavy user of OpenClaw as soon as it started. Kinda changed my world and have been using, you know, primarily Claude, Opus, and Sonnet as my as my engine for writing code.
And I'm a heavy, heavy user, and I was on the, you know, the max plan, $200 a month. And when they shut me off on that just recently, I was I was in the middle of a project, and I was so productive. I just couldn't make a switch, so I just paid the paid the toll. And just in the last, like, couple weeks, I'm I'm up to, you know, $900 in API spend on top of my $200 plan. And I'm just spending, like, you know, an insane amount of dollars a day. So it it becomes, like, very expensive. And I don't know how somebody
I mean, you know, I'm I'm blessed to be able to afford it, but, like, I'm I I don't know how, like, an average person can spend, you know, thousands of dollars a month on these plans. So I think you guys are are building something that's really interesting at the right time. I've I've heard David, you know, showing Morpheus in signal for a long time, and and now I'm finally checking it out. And I've got GLM five running as my primary agent. I'm still gonna probably send my heavy coding work to Opus four point seven,
but I'm I'm curious to hear what you guys think about, like, really deep coding tasks with these open source agents
David JohnstonThat's great. Awesome. Yeah. Glad to have you here, Micah. It's yeah. No. I've I've been talking about Morpheus for a while, but I think it's really hitting now because people can see the practical use. My feedback would be GLM five. I find good for documentation and a lot of the lighter stuff, especially writing. But I would really encourage you to check out GLM 5.1 for AgenTeq engineering.
So for most of the heavier code stuff, I'm using GLM 5.1, and that just came out last week. And so it's it's very, recent, And it's right up there, I would say, between a quad 4.6 and something like that. Well, pre pre quad 4.6 getting a lot dumber. So it's probably actually benchmarking above quad 4.6. And I I find I can get the same things done if I'm articulate and descriptive on what I want done and how I want it and done. And I would say
I'm getting the same results, but maybe, you know, something that took me twenty or thirty minutes is taking me thirty or forty minutes. So slightly longer set of cycles, but I'm getting the same quality. And I would encourage you if you wanna save a lot of money, what I'm finding is I can code perfectly well with 5.1, and then I'll just have a model like Grok do an audit. And so I'll use 4.2, which is the best cybersecurity auditing model in the world right now, even better than Claude,
for for just auditing the code. And so I've included that in my process. So I'll have, you know, the cheaper agent, you know, GLM 5.1 do most of the coding, and then it hands off the coder. We copy and paste it over to to Grok. I ended up just giving it the the API key to Grok and saying, you know, on on the coding step, go and get it audited by Grok. And it'll go back two or three times. Grok will find errors that it didn't see, and that's that's a big unlock. If you do cross model auditing,
you get much better quality code because the models are good at passing their own tests. But if you take it over to another model out of context, it'll find a lot more bugs. So I basically get it to go back for three or four times, and it end up with really high quality, but at a fraction of of the cost. So
Micah WinkelspechtYeah. With with TriNet now. Adversarial reviews. Often, I'll have my you know, whatever I'm working on. I'll even use the same agent and do an adversarial review. I agree that they're probably better at passing the test, but I still find it really helpful if you just tell the agent to attack its own work from the other side.
Kyle (Bow Tied Blue Fin)Yep. I think you made a really interesting point, David, on kind of giving it the rate requirements. Right? I think that Opus one of the things that Opus and and not even any version of it specifically, but overall as a model is very good at working in isolation. Right? But you don't necessarily need that trait of the model when you have a coding agent running or at least a
skill that facilitates agent like experience with it, where sets the requirements, create an implementation plan, create tests, run through the implementation, run through the tests, validate it. Right? When you go through that process, you're able to use something like GLM five one more easily because the structure's there. Right? It doesn't have to be inherent in the model weights. It's able to go through and and run that process and get the results and iterate on it rather than the one shot result that you're looking for,
or that Opus was maybe trained on a little bit better. So I think it's a I think it's it it's a really strong comment on maybe how we're doing things is going to change a little bit, and maybe we're going to act more like, you know, software engineers, right, rather than five coders. Maybe we're gonna get a little bit more there rather than, hey, build this thing to, hey, these are requirements. Build it, and the coding agent can kind of help facilitate that, which will allow us to use these open source models more and more and more until,
the market kind of converges there.
David JohnstonYeah. Well and maybe a good word for that is a harness. Right? I've ended up, you know, building a standard operating procedure for coding. Right? And it has 10 steps. Right? Before it starts coding anything, it does the research. Right? And sort of grounds itself in reality, like what's available? What are the tools? What are the best practices? Okay. Here's here's the research. I'm gonna build an architecture based on this research. Then when the architecture and the specification is clear, okay, go go to code. And what I found is if I spend five or ten minutes on the first couple of steps there, I'll save myself an hour
on the coding back and forth because it it's not doing that research as it codes and realizes x y z isn't available or whatever assumptions it had, you know, get blown out of the water. And so, you know, I really recommend to anybody that's using this, build your own process. I'll go ahead and open source my my SOP. I'll I'll post it on x. I think I've I've put it out there a few times, but now it's got all the stuff. Right? You're saying, Kyle, we need to get to the point of basically a gentic engineering. I think that's what we're gonna get to. Right? My my process now includes not only testing, not only auditing the code, but I'm looking for regression. Right? Did I lose functionality? I'm looking for dependencies.
Did I introduce something new that the software needs to now know to download or include in the install? So you end up with all these best practices, document what you built at the end of the process, push it out, you know, get GitHub to build the docker, all those steps. Once you've got that process down, you know, it it's become easier and easier. I've gone from basically having to handhold the whole process to giving instructions at the beginning and just approving outcomes at the end. It's getting really smooth.
Kyle (Bow Tied Blue Fin)Absolutely. And the our learning curve has reduced to zero because this can be as simple as injecting a skill file and slash start coding. Right? And then it kind of just walks you through that process. Right? That that's where we're at now where, you know, one, our willingness to try new things and our willingness to alright. We're gonna go about this a different way that's gonna save me 90% per month. Like, alright. Hell, yeah. I can now, you know,
develop three times as much, you know, output here, four times as much output considering my time that I have to harness it. But I I just think we're in a in an amazing time in this and seeing this open source trajectory and the tools to support that advance so quickly is, you know, just really excited about it. And I think Morpheus is positioned incredibly well to kinda facilitate, you know, the infrastructure for that market.
Bowen BelmerHey, David. That's the, chief Normie correspondent here. The people are asking, instead of an SOP, have you simply asked your agent to make no mistakes? Thank you.
David JohnstonOh, yeah. That that that definitely helps. But, you know, what what I found is I'll tell it to follow the SOP and then I kinda remind it. One of the big unlocks there recently has been memory. So once I got the memory in my OpenClaw properly configured because remember, it does not come turned on. If you downloaded OpenClaw and you never turned on memory search, it's just sitting there and not getting used. So as soon as I got that properly configured and sort of really got the memory better flowing,
now it's learning more and more of, you know, I don't have to correct it as much. Oh, I know to check for this. I know to go do the audit. I know to come back for the approval. Right? And so I'm finding myself having to give it less reminders. You know? So that's that's one of the things. You know, we talked a little bit about memory last week, and then we're gonna kinda touch on it this week. There's been a a couple of big things as far as MemPalace and Neo four j had some announcements, and I love to get into that because I think that's that's one of the other critical pieces of this. It's not just
the inference, but it's using the other open source tools that are out there, to improve your context Yeah. And the information you're giving your agents. Speaking of MemPalace,
Bowen Belmerso it's a great transition. Last week, our unexpected celebrity chime in of the week was the the existence of Mem Palace. Although we don't have a specific unexpected celebrity chime in this week, there was follow-up, news or maybe even a little bit of controversy surrounding Mem Palace because of the the realities of of what it is doing in its output relative to the benchmarks that it was publishing. David, do you wanna speak on that a little bit? I think that's a great transition to what you were just talking about.
David JohnstonSure. And there's a bit of a nuance here. Right? Like, again, a lot of these benchmarks are strictly does it work if you run it once as opposed to run it a few times, and so that's called zero shot or one shot benchmarks. And initially they had sort of touted a benchmark that, you know, is is sort of fair if you run it a number of times. Right? And it checks its own work kind of thing, and then you can get really, really high numbers. A lot of people, I think, to be honest, their competitors did not like that, and we're like, well, technically,
if it's only a one shot, it would be, you know, way less than a 100%, 90%, or 80%, or 40%. So it's hard to tell what of that what percentage of that is, like, their competitors don't like the tool because they open sourced it. And there was a bunch of stuff that you could use before, but it's all paid. So I think some of that might be competitive, you know, positioning, but I think some of it's fair. Like, the the team, Ben and and and his co cofounder both came out and said, yeah. That's fair. You know, here's what we think are better metrics, and we ran we ran it, you know, against these other benchmarks,
and here's where it comes out. And, you know, it's an open source project. It's MIT. Right? License. So a bunch of people offered PRs and improvements, and I know there's been a lot of iteration. I'd love to get the the inside scoop. We have some of those folks in our community, and they're they're from what I know, they're Morpheus users. So, you know, maybe we'll we'll get the inside story at some point, but, you know, I think I think it's a cool experiment and it caught a lot of people's attention. And for me the big benefit is it forced me to go and look at how my memory was working, which it wasn't,
right? And fix that in my agent and then I rolled the skill around MemPalace. But I think these tools ought to be agnostic. If you're using a big dataset, you should probably using Neo four j or something stronger like that. It's also worth kinda unpack the technical side. What is MemPalace? It's ChromaDB. Right? That that's what they're using under the covers. Beyond the schema they came up with and using the memory palace reference points, but it's ChromaDB.
So what you're really saying is what's the performance of ChromaDB versus Neo four j or graph databases. And there, think it really depends on your use case. So I don't know if Thomas or or Kyle have a a hot take on this, but I'll defend the the MemPalis people a little bit and say, you know, I think it's a it's a good open source experiment. It's been useful for me. It's working for me. Right? So, you know, qualitative stuff aside, qualitatively, like, it massively improved my agent. So, you know,
I know what you guys think.
Thomas BorrelI have mixed experiences with memory, right? So I started working on that maybe a couple months ago, and it got better, but then eventually it got worse. So I think there's a scalability limit that we hit pretty quickly when we go with tools like a ChromaDB or even the QMD that Toby built, which is searching through real markdown files.
And I think the answer is going to be really looking at a combination of systems, at least for now. I really like the approach that the team had taken for But then, would it really improve the results? After seeing all the controversy, I sort of paused the rollout of Men Palace within my own system to
see, like wait until it stabilizes a bit because I think it's easy to jump from one system to another to another. I tried one, stayed with one for a couple of months. It was amazing at the beginning, and now it just doesn't work as well. And so I wanna, I think it, I want to wait until there's a little bit more sort of market feedback before I experiment with one.
You know the other side to that is how your agent actually utilizes the memory that they have access to, which I think is another problem and one that personally I've run into, particularly with OpenCLO. And I'll just read a response that I got this morning from OpenCLaw when I said, why do you keep forgetting? Is that information, the issue that we run into, not in your memory. N d? And the answer was,
the problem isn't missing documentation, it's that I'm not checking it before acting. And so that's, I think, the first problem that I want to spend some time on because you can have the most amazing memory system behind the scenes. If your agent just forgets to check it, then it doesn't really add any value.
David JohnstonYeah. No. That's that's good feedback, Thomas. I I ran into something pretty similar. You know, you gotta you gotta train it to follow that process of checking and searching its memory before it goes and gives a response. And so some of that ended up, you know, prompting me to improve, you know, the soul and the user files and stuff like that. So it it does those checks
Thomas Borrelmore regularly as per the process. They're in there. It just chose to ignore it. And, you know, I know that's a that's a different discussion, but that's my number one reason now why I've switched from OpenClaw to Hermes. And I am using Hermes 95% of the time and OpenClaw's down to 5% to the point where I'm about to uninstall OpenClosed and really focus on Hermes because the other
experience I had was asking Hermes a question and Hermes coming back saying, we actually talked about this not so long ago. Let me start from where we left the conversation off. And I thought, okay, that's a change. And that's a change that I like, right? It's not like everything got reset overnight, and now you have a new you have a brand new intern that just started this morning that you have to train all over again.
David JohnstonThat's really interesting. I've seen Hermes is doing extremely well on adoption. If you track the number of stars on GitHub, it's now a top project. I think we're gonna see more of that, and it's worth pointing out to folks. This is one of the reasons this week I rebranded Everclaw to the Morpheus skill, is think Everclaw maybe sounded more like it was an agent as opposed to
this skill that gave you access to inference and decentralized AI. And so it's worth emphasizing the Morpheus skill works for Hermes, for Open Claw, for Iron Claw, for whatever agent you want to power, Morpheus works across all of them. Right? And the Morpheus skill specifically, I put up a placeholder website, morpheuskill.com, and you can check out all the content. But it's basically a series of MD files, so any agent you give it to is going to digest those MD files,
make it part of their system, add those skills, and then be able to be powered by this decentralized inference. And so I think that's an important note, is the Hermes folks have been involved in the Morpheus ecosystem almost since the beginning. In December '23, NEWS Research was fine tuning models and contributing to Morpheus code base and so big credit to those guys for continuing to iterate and moving beyond the fine tuning into
into agent building, which is really, really cool to see. So it's it's funny how many of the projects in the ecosystem, you know, were there during the early days of Morpheus and have been involved. So, yeah, it's it's really cool.
Bowen BelmerYou beat me to it, David. That was the next thing I was gonna bring up was the rebranding of
David JohnstonEverclaw to Morpheus skill and why that's important. Yeah. Well, I mean, I think it it'll be more clear. I've gotten good feedback from people that that's a lot easier for them to them to get. And so yep. Hopefully, I'll be pushing out a new version today. I'm just working on a new version of the the skill guard that's more intelligent. So, you know, Morpheus, you know, in order to use it, you sort of need this pack of skills. Right? You need good security. You need a wallet. You need to be able to hold the tokens. You need to be able to store your passwords.
So there's sort of all these complementary skills that go in to adding the Morpheus skill to your agents. So excited about maintaining that and it's been a lot of fun. Like every time there's a new version of OpenClaw or Hermes or whatever, you know, I'll roll an update and push it out to the community. But just gotten a ton of great response and that's got the API gateway built in, so it makes it easy for people to, you know, never have to even sign up for Claude in the first place. They can just go straight
into using Morpheus. And then as a bootstrap key included. So if you set up your Morpheus skill, set up your Hermes agent, you know, it'll automatically start using the Morpheus API and and get you basically set up with your agent enough that you can go and get your own key. But there's no sort of cold start problem, which is one of the big things that I want to, to fix.
Bowen BelmerAbsolutely. That we ran through our whole list. We had a ton to cover this week, which is awesome. The only other thing that I had on on our formal list of things I wanted to make sure that we touched is just our our eating our own dog food section. Or if anyone has, like, a specific, thing maybe that they use d a I for or AI generally over the past week that they wanna talk about, I like leaving some open space for that. I I guess I can start just with a really quick one. Since I have now
discovered how good my agent is at taking Excel spreadsheets and turning them into HTML dashboards that I can store offline and just access from anywhere, I've been obsessively taking, like, every single thing I use for my real estate business and turning it into some form of dashboard to mess around with. So not exactly a a super crazy application, but It's fun. It's been fun. It's been I've been enjoying it.
Kyle (Bow Tied Blue Fin)It's not a super crazy application, but it's a super valuable one. Right? Like, it doesn't It saved me time. Yeah. Like, quite a bit, actually. Everything doesn't have to be you know, we don't have to change the world with with every application. I think it's more of integrating AI and integrating these things into what you're doing on a daily basis is going to be, like, some of the low hanging fruit that it could expose us to how do we how do we augment ourselves with these tools rather than kind of one off use them for for super important things?
Bowen BelmerYeah. Fair enough. That is certainly done for sure. It probably shaves an hour off of, like, a couple different tasks that I've been using it for. Oh, did I lose you guys? No. You're good. Oh, okay. Sorry. I wasn't sure. My my screen flickered. Yeah. How was that was all I had this week? Mean, is is there anything else anyone wants to make sure that we cover while we're all here? Can I ask you a question? Yeah. Go for it, man. Of course.
Micah WinkelspechtI'm I'm totally new to this world here with you guys. So can you can you explain to me a bit about the back end of Morpheus and, you know, the the actual compute network? How much of that is, you know, bootstrapped by the founders? How much of that is is people joining the network and just adding compute? Are you using, like, Akash on the back end? Like, what's what's the back end look like?
David JohnstonThat's a great question. I'm happy to to take that. So think of Morpheus as an inference marketplace. So, you know, there's no Morpheus company. Right? It was totally fair launch. There's no founder pre mine or anything like that. So everybody involved is an open source code contributor. Folks like Kyle and others have have put up infrastructure like the API gateway, which is all open source. A lot of the inference comes today
from people running Venice. So maybe they own Diem or something like that and they want to offer models on the Morpheus marketplace. They can list those models. So they just download a node. There's a peer to peer node system in Morpheus. Anybody can download a node and say, hey, I'm a compute provider. And they could be running their own GPU, their own data center. They're using some third party. But certainly, yeah, folks have used Akash in the past, though less less now.
More people have been shifting towards systems that offer the inference, not necessarily just the GPUs. And so, Kyle, I don't know what color you wanna add to that, but, you know, it's this open marketplace, and and people can are mostly offering the open source models right now. There's nothing stopping somebody from offering a a closed model. But right now, today, I mean, they're just so much cheaper. The open source models are are most of usage. If I look at the stats, I think the most popular model is GLM,
and after that, it's Mistral and some other ones. But, you know, Kyle, you could probably get into the details.
Kyle (Bow Tied Blue Fin)Sure. I'll I'll just give some quick insight into, I guess, how the system works from the the actual infrastructure standpoint. So pretty much, yeah, completely open two sided marketplace. We're talking more specifically about the provider side. Right? So when you wanna provide to the marketplace, you're gonna host a provider node, right, that connects you locally to the blockchain to allow to for other, you know, consumers to go and run inference against you. Right? So within your node configurations,
it's as simple as where does this inference come from. Right? You're either going to set a URL, which could be local host. It could be, you know, like David said, OpenAI, right, if you wanted to offer OpenAI for some reason that I have no idea of, or if you wanna proxy to something like Venice or wherever else. So it allows you to go, you know, local host connection, a connection to Akash, a connection to RunPod, and then, you know, if there's an associated API key, you can include that.
I personally have done a lot of bootstrapping in the system. I've bootstrapped through Venice. I've bootstrapped through localhost on an, like, an AI rig that that I run. And, I found that although I love Akash, like, I'm I'm a huge supporter, I found that Akash is good for some applications with some GPU types where other products like Vast AI or RunPod or or there's a million of them
are good for other types of GPUs. So I was hosting some text speech through BestAI and RunPod. It it's really nonspecific. Right? It there's a difference between capability and then what's happening right now. I would say, I'm sorry. This is a long response, but I would say right now, it's primarily bootstrapped, and we expect that as more demand continues to flow into the system, providers will see that opportunity to go and capture some incremental revenue, right, whether they have excess capacity from something they're hosting themselves
or they just find a nice arbitrage where, hey. I can go host this model and and charge lesser than someone in the system or or they're overloaded, I can pick up some of that extra demand latent demand that's there. So bootstrap now and and we you know, not fully bootstrap, but part mostly bootstrap now, and we expect, that to to expand, you know, kinda starting immediately as this demand is really, you know, beginning to pick up.
Micah WinkelspechtAnd is there is there any arbitrage now? You know, if I wanted to help contribute inference to the network, is there, like, you know, cloud provided GPU services where where there's enough incentive on top to run inference on this network or or maybe assuming a little bit of growth in the network? Or or do you really need to run your own hardware in order to make it viable?
Kyle (Bow Tied Blue Fin)I would say right now so we could talk separately on some of this. But right now, there's probably not the largest opportunity because through some of my bootstrapping, the pricing is extremely low to incentivize demand. I would say this is gonna be a little bit of a of a a cat and mouse type game, right, where when, you know, there are some limits on my side to to what I can bootstrap,
then the the next layer of pricing will be much higher, and I will similarly be able to to increase the pricing accordingly to to be able to provide more. So I would say, today, let's, you know, let's get you in there, and we can we can figure out how to, configure the pricing properly and and figure out if there's any incentives to be to be made there. But, I would say current step right now is we're looking to drive as much demand as possible. And, from the provider standpoint, that will that should immediately follow.
David JohnstonWell and, Micah, to answer it in a different way, the arbitrage is the $25 per million tokens that Claude is charging versus the $5.50 per million tokens that, you know, it costs on on Morpheus. Right? And so anybody that can come along and convert people that are using Claude today over to, you know, GLM 5.1
or similar models, there's like an 80% arbitrage there. Kyle's talking about the arbitrage between the cost of running the machines and the various providers on the network, but the much bigger arbitrage is converting over those people that are paying through the nose for Claude today, and there's a whole universe of resellers, affiliates, people that ought to be building products on top using cheaper inference on Morpheus.
And as far as their users care, it's 50% less, it's 60% less, and whoever's building that interface
Micah Winkelspechtis taking some of that margin. I think that's going to be where a lot of the demand comes from is people building stuff on top. Yeah. I think my question is more rooted not not so much in my personal game, but rather trying to understand whether the model is sustainable at 80% discounts. Like, you know, aside from aside from the founders bootstrapping and subsidizing. Right? So
David Johnstonthink that's Well, that's sort of what's unique about Morpheus. There are no founders. Right? There was no pre mine. You know, the original white paper authors were anonymous, Morpheus, Trinity, and Neo. Nobody's heard heard from them since 2023. Right? And so in the absence of a treasury, it is sustainable. Right? There's nobody subsidizing that 80%. That's the natural 80% less that it costs to run the hardware and the electricity for these open weight models versus what you have to pay you know, an Anthropic or a ChatGPT.
Right? Because there's no license. It's it's like saying, you know, Linux isn't more compelling because it's subsidized. It's more compelling because there's no Microsoft sitting on top charging a $100 a seat for a license. Right? So you're just ripping out that that license and copyright structure, and you've got a an open weight model that nobody's charging a license fee on.
Kyle (Bow Tied Blue Fin)Yeah. I agree. I think that I think on both sides. On the consumer side, there's a clear, you know, arbitrage is probably the wrong word, but discount for the open source compared compared to closed source. I would say on the arbitrage opportunity as a provider, there will the arbitrage will come mostly from hosting local, you know, or self hosted options as compared to someone who just comes in and and resells OpenRouter. But it's gonna be a margin game. It's gonna be a
what are you offering, and is anyone else offering it? It it's, you know, no different than the dynamics of any kind of open market. Yeah.
David JohnstonCommunity is basically doing price discovery, not bootstrapping. We're we're we're past the the the early bootstrapping where, you know, it was experimental and, you know, it was come come build this. Now it's come come use it. Absolutely.
Micah WinkelspechtWell, I'm giving it a shot this week, so, I'll let you know my feedback on the signal. Cool.
David JohnstonAwesome, man. Good stuff. Alright. Well, Bo, thanks for emceeing as always, man. This has been a great session. Again, it's so cool to see, you know, people getting real utility out of this. And I think this is just the beginning. Right? This is the worst the models will ever be. Like, we're in in a week or two, we're gonna be talking about, you know, DeepSeek four or whatever the latest greatest model is, and, you know, it's gonna continue to sort of erode, I think, the lead that, you know, Claude and others had. So it doesn't matter if you're using it for price or privacy
or reliability. You know? It's really cool that, you know, so we're at this moment right now where where we've crossed that chasm, and and people are getting real daily use out of it.
Bowen BelmerYeah. Absolutely. I I think well, and thank you for thanking me. This is a huge highlight every single week. I appreciate it, and everyone who joins and everyone who listens. The the thing that has just rung so true week over week, month over month, quarter over quarter since I discovered Morpheus, jeez, over two years ago now, which is really crazy to think about, is that all of the principles, like the anti fragile nature, the
on on top of the fact that, like, the tech the tech is improving, to your point, this is the worst the tech is ever gonna be. It's only gonna get better. But then on the other side, the non tech pieces, like the the freedom principles, the access, to intelligence that's unobstructed by central parties, the ability to have a network that can be accessed from anywhere permissionlessly, all of the other aspects of the world, like geopolitically, have also just continued to trend in that direction. And so, like, the those stances that the community has from my perspective just continue to get validated over time.
And, eventually, those two things, in my opinion, will just completely converge. The tech will be at the perfect points. The values and and, like, the recognition from the public will be at the perfect point, and, you know, then we're on a a rocket ship for everyone to ride together. So, anyway, it's been awesome to see and look forward to, you know, continuing continuing on. So thank you as always to everyone for joining us, whether you're a panelist, speaker, or listening live, or listening to the recording. Shout out to the mere Morpheus guys for doing the
kind of remastered recorded versions. And with that, I look forward to seeing everybody next week. See you guys. Keep being awesome. Take care.
Zion, hear me! For Season 2 of the Mere Morpheus podcast I'm going to be uploading the Morpheus builder weekly updates. My reason for doing this is to make it more accessible for those who want an update directly via...
Zion, hear me! For Season 2 of the Mere Morpheus podcast I'm going to be uploading the Morpheus builder weekly updates. My reason for doing this is to make it more accessible for those who want an update directly via...
Zion, hear me! For Season 2 of the Mere Morpheus podcast I'm going to be uploading the Morpheus builder weekly updates. My reason for doing this is to make it more accessible for those who want an update directly via...
Zion, hear me! For Season 2 of the Mere Morpheus podcast I'm going to be uploading the Morpheus builder weekly updates. My reason for doing this is to make it more accessible for those who want an update directly via...
Zion, hear me! For Season 2 of the Mere Morpheus podcast I'm going to be uploading the Morpheus builder weekly updates. My reason for doing this is to make it more accessible for those who want an update directly via...