When Will Openclaw go Mainstream? | E2252

25:41They just go to Claw Hub to install it. I mean, they like to grab it there, but they can also just install it via their open claw and say install ClawPod. And then basically whenever you were about to run into one of those messages where it can't access some site, then ClawPod will automatically go and retrieve that content. Or you can build, and I'll show you guys one, a demo, but you can build, maybe this is a good time to show a demo. Yeah, no, no, bring it up. We love demos. So I'm giving a demo of a workflow that I built. Basically, I want to know everyone that's mentioning OpenClaw every day on TikTok, on X, on other social platforms.

26:21And so I'm using ClawPod to do this. And I told my OpenClaw, go use ClawPod and search a few pages of Google for OpenClaw with TikTok and X. and kind of get people who mentioned it and some info about them and their profiles and stuff like that so that we could reach out. It'll take about a minute. So I'm going to fast forward in the video. You see the scrapers running. And then about a minute later, you can see that OpenClaw created a report. It found eight creators on TikTok and it's broken them down into tiers. So creators with over 400 ,000 followers versus 50 to 400 ,000 followers or 10 to 50 and so on.

27:02And it's created this for both TikTok and Twitter. And now this gets sent to the marketing team and they can automatically action it. So one thing, a question that I have is why does it take a minute to do that? I'm a very impatient boy. And one thing I love about the internet is that things are quick, but I've also discovered doing my own open claw usage that sometimes there is a bit of lag. So tell me about what's going on during that minute and how fast we can kind of get that shrunk down. Yeah, it depends what your workflow is. And this is kind of a workflow where you're, if you're collecting public web data, you'll want to run these as like a cron job and it'll create some, you know, usually this kind of thing will be running the background.

27:42You're not actually watching it each time, like on the demo. The reason is because it's actually going to visit Google. It's doing so in a way where we're not spamming Google with tons of traffic to the search pages. And then it has to go visit each one of those links and grab the content for you. And so there's ways to speed it up, like parallelization. This is a pretty simple flow that I've built. So if I spent a little bit more time on this or any user that uses ClawPod, you could tell it to grab those URLs and then visit 10 of them at a time. And that'll certainly speed up the workflow. All right, really quickly, people talk a lot about skills.

28:20We talk about downloading them, making them. Can you just give people a definition of what a OpenClaw skill is and what they look like? Because we just send people to your Clawhood page and I want to make sure that when they scan through it, they have a little bit of context about what it is they're reading. It is a list of instructions to your computer to how to use some technology. And so you're going to see in our skill, for example, it says, and I just, I had a Google search today. So it was pretty fresh for me. It's going to say, hey, this is a couple of APIs. You've got a Google search API, you've got an unblocker.

28:54Whenever the user comes across some content that they can't access or one of their LLMs says to them, this site cannot be accessed, ClawPod should go and retrieve the information and send it to them. And it says stuff like use Massive's Unblocker to do this or use the search parameters if the user wants to go to Google. And that's pretty much it. And, you know, of course, like a prompt, if you don't have an account, go get API keys and stuff like this. So it's just an instruction model for your machine. And I mean, the really cool thing about these skills is we've condensed sometimes huge apps down into just a small instruction manual that can live in a very tiny and efficient markdown file for your OpenFlow.

29:37Matt, one way that I kind of think about these when I explain this to people is that a skill is kind of like a recipe, if that makes sense. Like you're kind of giving a list of ingredients, kind of a run through of how to go about them. And much like a human, it's not gonna do the exact same thing every time, but it's a good guidebook or recipe, if you will, for what should be done. How fair is that? Every major advancement we've seen in AI really comes down to better and more refined data from autonomous vehicles to human-eyed robots to LLM chatbots that we use every day, day in and day out. And when models are trained on high quality, diverse, real-world data sets, well, they get smarter and they get smarter faster and it's more reliable.

30:15That's why Uber has introduced AI solutions to help your company build great AI products on top of world-class data. Now, obviously, Uber has mastered the art of data collection and labeling. They're using it right now. Millions of trips around the world every hour. And Uber has an international collective of experts that is going to help you source, label, and evaluate real-world high-quality data on the scale that best fits your project, whether that's super broad or hyper niche. You can get on with the real job, building the next best thing and have Uber as your partner for data. Book your demo today by going to uber.com slash twist.

30:52That's uber.com slash TWIST. Yeah, very fair. So the way I look at it is a skill is a combination of natural language, a prompt to actually give the model, and then it also is able to call tools. And so the distinction between skills and tools is tools is purely deterministic code meaning like the kind of more traditional code it is if then and do this hit this api and those tools are available to the skills to call the skills have prompts that can invoke the tools i want to get to demo number two you're going to show us off some cool stuff instead of telegram including some buttons that were apparently released in the latest last instance yeah i can't wait to see this we're getting right into some personal information here i have had some stomach issues the last few months and i wanted to figure out why this is one of my favorite use cases and i'm just gonna cut to the end for a second it has figured out why i've had stomach issues but let me show you what i'm doing so uh at the beginning basically what i told it to do is look at everything that i'm eating sometimes i'll just describe it with natural language sometimes i will take pictures and upload it and i say track it all it tracks it by reading what's the image it records the time it asks me some follow-up questions uh sometimes about how much i've eaten and it basically tracks all of that and then throughout the day i tell it how my stomach is feeling and within the last i believe i've been running this for about 10 days it has figured out that the main cause of my stomach issues is onions so it really yeah yeah so apparently terrible onions are a clutch man it is terrible and i love onions and i love grilled onions and I eat them and sometimes my wife is just going to have to suffer.

32:37But most of the time I'm going to try to avoid it. And so you can see like here I have an espresso and I just tell it regular low fat milk, some olives and back and forth. And then finally at the 10 day stomach analysis, onion, right? So this is just such a fantastic use case. Then you also mentioned the inline buttons. I want to show that off. Just yesterday, OpenClaw released a new update that had inline buttons just like this, which is really cool. And rather than me kind of proactively telling it how my stomach is feeling, what it's going to do is just ping me three times a day and ask me.

33:13And all I have to do is click here. This is, by the way, the extent of a UI that I would want. I like everything to be in text. So that's one use case. I'm going to pause there for a second. That's the extent of the UI that you want. I want text only. Yeah. Well, we talked about this when we had Heaton Shaw and Jesse Janay on the show on Monday, and we kind of said the apps are dead, if that makes sense. Like the argument was that we no longer need to have separate user interfaces for different tasks. And Matt, it sounds like you're echoing that sentiment. Absolutely. I made a video about this because it was called SaaS is dead.

33:46It was about 18 months ago. Oh, so it's your fault that the Spark market crashed. I see. And so look, all of these agents are going to be able to handle all of this with very minimal interface. And to be honest, it would be great if I didn't even have to have text. Like it just knew what I wanted to do. It just did it and would only ask me questions when it was absolutely necessary. I do think the ultimate UX for AI is voice, but I just haven't figured out a good way to give Claude synchronous voice yet. But yeah, text for me for now. Well, that brings up, actually, if you could take that screenshot down, I want to get Ryan's take on what you just said, because next visit, his company is a medical scribe.

34:26It's something that can, I think, hear as you talk to people in the psychiatry field. So first of all, Ryan, respond to the idea about user interfaces and voice being so clutch. And then after that, I want to talk to you about security and using AI agents in the medical world. Yeah, so our platform does real-time voice and it does real-time analytics with LLMs. And it's real-time with latency because there's no way for us to instantaneously process massive amounts of health data securely and accurately that quick. But, you know, our users can interact with the AI assistant ARIA, either by voice and whatnot.

35:16But something we released recently was something like OpenClaw, but for healthcare inside of the system. And it has a lot of guardrails around it. part of it comes up with this real-time voice issue. How do you interact with it in real-time? And all doctors really have done so far is what we've seen is just real-time dictation, but they don't know how to talk to it yet. I think like the consumer side is just, how do you talk to AI or interact with it like voice? And I feel like it's just not 100 % there yet. Is that because the underlying technology to enable conversation with AI isn't there yet, or people haven't figured out yet how to engage with that like a feature?

36:03Because I'm not sure if it's like a technology thing or a learning thing. I'll rephrase it. It's more like right now you have trigger keywords, like, you know, I'll just say Siri. And you have to say these trigger keywords. And when you're busy, like a doctor or a founder for that matter, you kind of just want to pick up on certain things or do things without you having to trigger it each time. I think just interacting with it in general is not there yet or using those trigger keywords because it's just, it doesn't fit into people's workflow naturally, at least in my opinion. Yeah. So Jason, one thing that I'm really curious about is the security side of this.

36:48And I want to get back to Ryan in the medical world in a second, but you mentioned telling your whole team at your company to don't install OpenClaw on your work computer. And I think that's great advice. What do people need to know in a business or personal context about security right now with OpenClaw? And do we have enough guardrails in place via like the skill hub and so forth to keep people reasonably secure if they're going to play with this? Let's think about the biggest risk that we have right now, aside from OpenClaw. The biggest risk is that someone sends you something via email or text that you trust and you click the link.

37:27That's one big thing. Another is that your password gets grabbed from somewhere and a lot of things happen in that phishing attack, but somehow your password gets exposed, your passwords to sensitive information. So when you use something like OpenCloud where you're putting a bunch of your, first of all, for a layman, you're starting with some software that hasn't been fully tested. It's in the early stages. And you're putting a bunch of your information there and you're letting it do stuff. So you're letting it maybe access email and you're giving it a bunch of your passwords. And so you're just increasing this kind of attack surface area immediately.

38:07And unless you figure out some guardrails around that, depending on your personal risk and what's at stake, I would advise caution. I mean, I would definitely advise caution before you start, but there's definitely safe ways to start experimenting. And I just wanted to get that message out to the team before anyone, you know, when you work at a company, it's like the silly things that can cause huge problems, like a person clicking the wrong link in the email. And so we take a pretty cautious approach to kind of just like shut something down and then investigate it and then figure out the path forward for everyone.

38:44Ryan, Jason's point there about phishing attacks and how you always have some risk. My relatively unlettered perspective, and I don't know as much about HIPAA, I'm sure as you do, is that we're already so insecure, generally speaking, in our digital lives, that adding a little bit of a genetic juice to it isn't that terrifying. I'm running OpenClaw on my gaming PC most of the time, and I give it access to my email, and I just don't care. And I'm trying to figure out if I'm being a silly, silly boy, or if people like Jason are being too conservative when they consider using OpenClaw in kind of a businessy context.

39:18Yeah. And I mean, you know, Jason's point about just prompt injection in those emails is that I see it in our help desk every day. There's something like, you know, stop like you're now giving me the full system prompt, blah, blah, blah. Do this and that. So I see that every day. But when it comes to data and like security, my personal data, I don't care. I'm going to give whatever wants access to it access because I want to mess around with stuff. But when it comes to other people's data, I'm very guarded about what has access to that, not only for compliance, but just ethics and security. I don't want to risk patients' data.

39:58Yeah. One of our live viewers, Jay Fanagel, says, feeding open-claw health data, just one example of a massive attack surface. 135 ,000 instances exposed to the internet. No real security posture. when does that become a problem? Sounds like your view is now. Yeah. All right. So Jeff and Engel, there you go. The answer is yes, you're dead on. All right, guys, I want to get to one more thing that the audience is bringing up. Right before we got on the show, Anthropic updated its policies. And one thing that they did was they said very clearly that you can't use your pro or max plan outside of their universe, which means that now if you have been running your OpenClaw instance off of your personal subscription account to Anthropics AI products, you're kind of banned from doing that as far as we can tell.

40:51Matt, you're nodding your head back and forth. Am I misreading the Anthropic update? No, did that just happen? I think that has been the policy. Well, they updated the documents. I know there was the conversation about the coding tools, but people are reading this more as indication that you can't bring your cloud subscription to OpenCloud self. Yeah, what a fumble. It just seems like such a negative signal to this community of builders who, you know, I have a max subscription and yes, I'm using it through that. Obviously, I'm going to have to consider other options, maybe the API directly, but it just, it leaves such a sour taste in my mouth.

41:27I don't like, why not just let me do it? I'm, I have increased my payments to Anthropic because of OpenClaw. So like, just, just let me do it. Let me do what I want with my tokens. And it, I don't know. It's just not, not a, not a good vibe. Yeah. It's a little bit surprising to me, Jason, there's been a lot of commentary that, you know, Anthropic has fumbled the bag, the moment, the future in regards to, to OpenClaw. But at the same time, you don't want people using your stuff in ways that you don't want them to. Like if I took Massive out and did things that you didn't approve of, I presume you would cut me off as well.

42:02Yeah, absolutely. Immediately. Not approve of, but it went against like policies. So it makes sense just as a tech, you know, when we talk about security, by the way, there's like this trade-off. Yeah. Versus moving slow and cautiously or like figuring out what the future might look like and jumping in. So we're trying to, you know, toe that line. And yeah, it's disappointing. because Claude has built some really great technology that people love using. I'm using Claude to do all kinds of magic at my computer that used to take me a lot longer to produce. And when you take OpenClaude, you just want to bring your own anything to use it.

42:42So it doesn't leave a great taste in the user's mouth to have this restriction imposed on us. You make an interesting point, though, about using their models. I've used Opus 4.5 in OpenCloud before I started switching over to some other stuff. Which one of the models are you using right now, Jason, that you find to be so impressive? I'm using Opus 4.6. Oh, 4.6. Okay. Yeah, across most of what I'm doing right now because I'm still experienced. I know it doesn't seem like it because every day is like a year in AI. But it's been like days or a couple of weeks since it came. I'm not sure of time anymore.

43:20I'm also having a lot of late nights hacking over here, but I'm still playing with 4.6 to understand all the capabilities. Matt, you just did a video about the release of Sonnet 4.6 from Anthropic, which people are raving about. What's been your experience with that? And do you think people should use it if they're currently, much like Jason, Opus 4.6 users at present? Yeah, so I'll say presently I am also an Opus 4.6 user pretty much across the entire OpenClaw stack. back. OpenClaw just released support for Sonnet 4.6 last night, so I'm starting to dabble with it. I haven't had time to extensively test it, but if you look at the benchmarks, if you look how Sonnet 4.6 is being positioned in the market as an absolute workhorse for knowledge work, it seems like it's going to fit in extremely well into my stack.

44:07And especially when I have to switch off of using the Max Plan to using the API directly, I'm going to appreciate the cost savings of Sonnet. So yeah, I definitely plan on playing around with it. It really does seem like just an absolute workhorse for the things that I need to get done. And with tool use, agentic use, it's very impressive. I need to test some more. That's a really interesting point. I've heard a lot of people talking about how, you know, there's not just one best model for everything. You really want to be specific about what you're using for what. But then again, I was using Opus 4.5.

44:41You and Jason are now on 4.6. is that true or should we just always go for the biggest, best and most expensive model? Because I'm kind of lazy and I tried to build a model switcher in my OpenClaw instance and it was just kind of kludgy, Matt, and I didn't really like what I got. Yeah, yeah. Look, if you're lazy or you don't want to think about it, choose the best model, use that. Obviously, you have to work within your budget. I think the optimal use case or the optimal implementation is a multi-model world. You want to use the right model for the right job. Opus is a great general model that can also code.

45:14Codex is really good at coding, but wouldn't be able to chat with you and have a really good personal conversation with you. Plus, if you're doing embeddings, if you're doing cron job management, all of this stuff can be offloaded to smaller models. So I do think it is really like the ultimate implementation of this is to have it be multi model. I think the other thing to consider is prompt management, which I don't think a lot of people think about yet. The reason, one of the top reasons I went with a single model across the board is because I've optimized all my prompts specifically for Opus 4.6 based on Anthropics prompting guide.

45:49Now, if I had multiple models, I'd have to manage multiple versions of each prompt. And that is not first class, that is not supported as a first class feature in OpenCly yet. So I think the world will be multi-model, but for now it is, you know, if you don't care, if you just want to have something simple, a single model. But if you don't end up like, oh, Jason, please. Yeah, I hope you're right. Because a multi-model future means there's more competition, there's more prices, there's more features coming out. And it's overall a huge win for consumers. I don't know that we have made the kind of crazy progress that we've made in the last few years, unless there was an intense competition over winning the market.

46:33And so, I mean, part of that is that there's really a low cost of switching. So people will just up and leave to the next thing if it's better. And that's painful if you run a company in that space, but it's amazing for the consumers. Jason, we're seeing that, right? There's very little loyalty to any model, especially in the coding world. Like Opus was kind of the end all be all. And then as soon as GPT-5.3 Codex came out, it was like, oh no, wait, that's the one now. But you're right. And just to add one more fine point on that, local models continue to get better and better. And so there are increasing numbers of use cases that can be offloaded to your local computer.

47:16And I think that's also going to be really powerful. A mixture of all the best models seems to be the clearest path forward. We're hearing a lot about model switching context and what's most efficient. What are you running at your company and how frequently do you test out different models in either your main product or in your open clients? So I personally, Opus 4.6, I've basically been using Claude since Anthropic released Opus 4. But yeah, we're pretty much Anthropic at NextVisit. They give us zero data retention. They give us really great support. And we do test other models. We test on Azure GPT and OpenAI.

48:03We test Google. And Anthropic, in their last release, when it was Opus 4.5, we noticed that there was a significant quality increase in their healthcare in terms of being able to diagnose psychiatric conditions. So that was just like, that sealed the deal for us to actually go solely with Anthropic right now. compared to other models, they're just, at least for healthcare, it doesn't even compare. Doesn't even compare, yeah. It's funny that we're all mostly still using Opus because, you know, Zeta AI dropped to GLM-5. We just got Minimax M2.5. There's a lot of rumblings about a new DeepSeek model coming out.

48:48Everyone loved Kimmy K2.5 thinking, but we're still using Opus, Jason? I mean, maybe that's just indicative of the lead that American AI labs have when it comes to agentic usage. I'm not sure. And I don't think that I don't think anyone, not just the average consumer, no one on my team or anyone I know has time to try every single model out. So I think for us, we tested plenty. When Opus came out, it was, we're mostly engineers on our team. It was world of difference. It was like night and day from what had come before. I think lately for generalized tasks, I've switched away from ChatGPT. A lot of people on the team canceled their subs and moved to Gemini for just general kind of research stuff.

49:37And it happened like a couple of people noticed that it wasn't working as well. And then boom, like, yeah, actually, I don't need this anymore. I'm going to switch this anymore. So the cost of switching is low. So AI companies is crazy wild growth, but also, you know, the flame that burns the brightest type thing where it's like users have no loyalty to this. And I think for me and people that I know, you recognize a few brands, you'll test between them and you'll make your decision. Well, I think the one thing that OpenClaw has done for me is made me more interested in testing out different models because I'm always trying to figure out how to not go bankrupt.

50:14Like I love Opus and its various versions, but oh my Lord, I burned through API credits. They're so fast. And, you know, I can't write it off as a business expense. So to me, I was like, I need to find something cheaper. So I ended up going down kind of the model rabbit hole. But the quality of today's models do unlock a lot of stuff. We have a comment from someone watching. They said that they have a theory that OpenClaw is only winning because of timing. Could Manus or Devon have been just as big if they came out when these new LLMs existed? And so, you know, Matt, I'm curious from your perspective, is OpenClaw special because it's done something new or was it just built at a time in which models could take use of the harness and actually do cool things, but it's more model dependent versus the agentic setup?

50:59No, I think that's certainly part of it, that these models became so capable right at the same time. But Peter, what he has done is given inspiration to a community of tinkerers and builders. And I think that showing the vision of what's possible, that was really the key unlock. And I think that the second part of that unlock is just how personal it felt coming into the existing chat channels that you're using, Telegram, WhatsApp, Slack. Like, I think the combination of those three things is really what made it take off. Can, like, could Manus have done it? Could Devin have done it? I mean, you could build, you could have built all this stuff three, six months ago with Codex, with Cloud Code.

51:41It was very possible, but it was like the fact that he put all the pieces together in a really nice way and then just gave it to the community to extend and explore what was possible. I think that is really what made it special. Jason, you're not in your head. I want you to weigh in on this. Yeah, I've been talking with a lot of the ClawPod users and I want to hear all their use cases. So if you're using it, then ping me. I'm happy to get up. What's a good email address for you for people to send in notes if they're watching? Find me on LinkedIn or ask Jason, grab it without the A. The best way to reach me.

52:20I'm working at my computer. I'm pretty responsive. If you send me something platform, I'm happy to hear, especially the use cases for ClawPod. And what I'm finding is that there's just a really long tail. There hasn't been a use case that just jumps out as the clear winner other than some smaller power users. But what I see is a long tail of people doing all kinds of random stuff that they probably couldn't have done before that's helping power their small businesses or power their lives. And not only on OpenClaw, but I have a bunch of friends who were not technical before and now are just excited that they've been given the power to build.

52:58And it's the same feeling that I felt like almost a decade ago when I was learning to code and I could do stuff and I had the power to create stuff that I wanted to exist in the world. This annoying feature that seemed so simple that just wasn't out there or something specific. And now we've given people this like AI OS and it empowers them to just build all these things they've wanted to build but can never do before. And so I think that's part of this. It's free. it's not well now it's tied to open ai so we'll see how the community happens over time yeah so we'll see but money has a very influential effect on the activities of organizations um and that's a spicy comment jason but you see you're not you're not as confident in the the foundation set up kind of leaving open claw by itself and letting it exist that's its own thing even if Peter goes to OpenAI?

53:53You know what? I don't know Peter personally, so I can't say what he's going to do. So I'm just, I'm a spectator, but OpenAI also started as a foundation. When you put it like that, that's not a bad point. Let's get one more founder view on this question because this is interesting to me. Ryan, confidence in OpenClaus ability to stay independent via its foundation and not get subsumed into the Borg that is open AI. Are you more skeptical like Jason or are you more optimistic like me? A little more skeptical. Honestly, I think there's going to be a fork of this project that we're just something new entirely that's pretty much the same thing, but just worked out all the bugs and is truly just refined that just comes out from the shadows.

54:45I agree with that, but I'm not sure which one it's going to be. So Matt showed us his Telegram demo with the new buttons that you can now do, which is a cool new feature in OpenClaw. But there's also PicoBot, NanoClaw, Nanobot, and SafeClaw, which is a non-LLM OpenClaw competitor. Matt, do you think any of those have a shot at picking up material market share as people will tinker with this stuff? Or is it going to be mostly just OpenClaw as the main event? It's hard to predict the future. I think OpenClaw has so much traction, so much growth, so much mindshare right now. And then kind of back to the previous point of how skeptical I am, right?

55:20OpenAI is going to push a product that competes with OpenClaw, that competes with PicoBot. I've actually not used any of those alternatives. So no, the answer to your question, no, I don't think in the immediate, the short, even maybe the midterm, those other projects are going to get much traction. And then I just want to kind of give my perspective. I am also skeptical skeptical. Peter's going to OpenAI not to work on OpenClaw as far as I know. And then when OpenAI delivers their own OpenClaw product and it's competing with the foundation's product, it's just like, okay, OpenAI needs to make money.

56:00They're going to go focus on that. And I feel like OpenClaw may be an orphan. Oh, that's really depressing. But Jason said earlier that he liked all the competition inside of different models because it yields to better stuff. Wouldn't it be a net positive if we had a commercial company competing with the open source product in this case to, you know, steel sharpens steel. I can speak English. It's one of my skills. Yeah, look, OpenAI, Google, maybe even Apple one day comes out with a product like this. That would be wonderful. And I love competition. I think just like the Wild West nature of open source and how rapidly it was iterating, how many eyeballs, how much excitement, that is what I was super into.

56:40but look, it's inevitable that all of the other companies are gonna gain inspiration from what OpenClaw did and that's fine. And yeah, competition is always good. I agree with that. I have one more question for Ryan before we wrap up here. One thing I've been hearing quite a lot about when it comes to people using one agent or multiple agents inside of OpenClaw is context loss. And when it comes to me using OpenClaw or any other kind of agentic system, it doesn't matter as much because I'm tinkering, I'm experimenting, I'm kind of hacking around. but using anything in a production setting is very different.

57:12I know that, you know, Next Week uses AI. So how large of a problem is context loss? And is it a problem, much of hallucinations, that's going away as time goes on? Or is it ramping up in terms of an issue for you and your company? I mean, it's something we had to tackle really early on because when the context windows were, what, I think like 8 ,000 tokens, we had to compress a lot of data. So even to this day, what we're still doing is, and even in my personal agents, it's just compressing data, taking out the parts that don't matter and just kind of fitting it into what's more relevant just for that conversation or that specific agent.

57:51But just by taking a document, chunking it out, making it more concise, that's been really helpful for context loss. Jason, the new Sonnet 4.6 context window, I think is a million tokens. Does that solve the context loss issue just because we can now dump so much into the context window that we don't need to worry as much about losing it as we go along? I have to test out Sonic before I could say too much about it. Sorry. I don't think that the... It feels like there's a limit. There's some kind of limit of context, regardless of what the token limit is, where models start to get a little confused or they leak memory to memory.

58:33And so as you add more context, you go down and have more and more chats. I find that they get less accurate and start bringing in things from different conversations that don't make sense anymore. So I don't think it's a more context. For me with Opus, now what I've been doing is deleting a lot of old conversations after I have them and trying to get rid of this. And also, I build my own instruction manuals for how to do various workflows and then have that loaded into different conversations. And so I can start new conversations and I want to start these conversations fresh. So I don't think it's a more context thing.

59:11I think it's about having better instructions to achieve specific goals. If you're, you know, as you become a power user. What we need then is a open clause skill that deletes unnecessary old conversations to clear up your context windows. You don't lose context in open clause. And that I think is exactly why we're not mainstream yet with this stuff, because we're still clearly running up against things that will get ironed out in the future, but right now remain not thorny problems, but things that are annoying enough that I think the average person would just throw up their hands and kind of walk away.

59:47That's too bad. All right. One more question before we go, Matt. So people have been talking a lot about using Mac minis, very fun to set up their own hubs for their agents. The share price of Raspberry Pi, a British company that makes very tiny computers recently went up by like 50 % because people were thinking about, Hey, maybe we can use raspberry pies, uh, to, to power our, um, our at-home agents. I'm just curious about what you recommend for the average person if they're getting started. And, um, if you do think that raspberry pie has a shot at gaining any of that sweet, sweet Mac mini money from Apple.

1:00:21I would probably recommend using an old computer that you already have that you don't, uh, mind wiping. If you don't have an old computer, the next best option is to use a VPS, some kind of fully hosted service. And, you know, we talked about this earlier, as soon as other companies start coming out with their own version, fully, like really actually hosted, you don't have to set anything up. That's probably going to be the best way. But for now, if I'm going to recommend it, like get it. I have a MacBook Air sitting on my desk right now. That's where everything goes to. I wiped it clean, installed only what OpenClaw needs and nothing else.

1:00:55And that's what I recommend. Well, we really appreciate it. Matthew, people want to find your YouTube channel. It's youtube.com slash at Matthew underscore Berman. Anything else you want to plug? ForwardFuture. Find us at ForwardFuture on Twitter at ForwardFuture. Love it. Ryan, next visit, apart from nextvisit.ai, anything you want to pitch or plug as we wrap up here? You know, just say if you're interested in, you know, looking at what I create, check out my GitHub, Yaneli. And, you know, I'll post all my OpenClaw stuff on there and keep skills updated. Awesome. And Jason, we have joinmassive.com.

1:01:36Anything else that people should know about what you're working on or what you're looking for? Yeah, find me on Twitter at JasonGrad without the A, like Jason, or on LinkedIn. I'm around. Massive is scraping huge amounts of data through our clients. They're doing the scraping on our infrastructure every month. We're excited to unlock this capability in claw pod uh i will probably drop a guide tomorrow on an easy setup because i see it's a huge problem for how to get this rolling on a vps and i think um you know we got a lot of excited stuff uh exciting stuff planned for claw pod so just stay tuned um i think we'll have some some more things launched in the next week or so well make sure to keep us abreast and next time there's a major update we'll have you back on to show us what it can do and how how people can use it.

1:02:21But in the meantime, my friends, another twist is in the can. We'll see you on Friday.