Maple AI co-founder Mark Zuman explains why giving an AI agent full access to your computer is functionally identical to installing a virus.
Mark Zuman, co-founder of Maple AI, returns to break down what's actually happening behind the scenes when you give an AI agent full access to your computer, and why the privacy implications of the agentic revolution should matter to everyone experimenting with tools like OpenClaw. Running an agent on your computer is functionally identical to inviting a virus onto your system, it gets full root access to read files, run programs, and scan your network, except this time you're welcoming it in voluntarily. The smart approach is isolating agents on a separate machine or VPS, but even then, connecting to Anthropic or OpenAI's API means all your data flows through their servers. Open-source models like Kimmy K2.5 are now on par with frontier models, but the tooling and middleware around them still lags behind, creating a bottleneck for projects like OpenClaw that want to run fully private. Maple is building an encrypted AI assistant with persistent memory that gets to know you over time, and the privacy guarantee actually makes it more useful because users are willing to share more when they know the data is protected. On agentic payments, Bitcoin faces the same merchant adoption problem it has in meatspace, agents directed to pay with Bitcoin will hit a wall if merchants don't accept it, and Stripe and stablecoin providers are already cutting deals to be the default rails. Mark also built an AI bot that joined the What Bitcoin Did podcast live using entirely local models for transcription and voice generation, proving that private AI toolchains can power real-time applications without touching a single closed API. His vision for the next three to five years: most people will interact with AI through wearable hardware, and if that hardware isn't open-source with reproducible builds, we're sleepwalking into a surveillance state that lives in our ears and on our faces.
"You're effectively giving some kind of computer software full access to your computer to run programs, to read files. It really is like a virus."
"That's what everybody's doing with their OpenClaw. They're getting a separate computer. They're locking it down with file encryption and everything. And then the final step, they're inviting Anthropic or OpenAI to slurp up all of their data."
"The most private AI can now become the most personal AI."
"We need to stop thinking that using open source models is a subpar experience. We just need to build better tooling around them."
"Don't get too emotionally attached to your agent. It's a tool that gets stuff done for you. It's not Scarlett Johansson in Her."
The agentic AI wave is here and it's genuinely exciting, but Mark's message is a necessary counterweight to the hype, know what you're giving up when you connect these tools to closed-source providers. The path forward isn't to stop experimenting, it's to build and support the open-source alternatives that let you keep your data while still getting the productivity gains. Maple's approach of combining encrypted infrastructure with persistent memory points toward a future where privacy and capability aren't trade-offs. For Bitcoiners, the takeaway is familiar but urgent: the merchant adoption problem doesn't solve itself, and if Bitcoin isn't ready for agentic payments, stablecoins and Stripe will happily fill the vacuum.
0:00 - Intro
0:45 - Progress at Maple
4:05 - What happens when you use OpenClaw
9:36 - The middleware advantage
13:45 - DoW and Anthropic
19:58 - Private AI is freedom AI
23:20 - Building AI with AI
26:09 - The future of AI interaction
32:07 - Local community models
37:26 - Advice for beginners
40:21 - AI podcast guest & newsletter
47:27 - Productivity boost
49:15 - Agentic payments
54:35 - What Maple is cooking
(00:00) You're effectively giving some kind of computer software full access to your computer to run programs, to read files. It really is like a virus. Back in the 90s and 2000s, we were like so nervous about viruses on our computers that we would install McAfee or Norton or whatever they were. And now we're like welcoming them onto our system, but they behave the same way.
(00:19) That's what everybody's doing with their open cloth. They're getting a separate computer. They're locking it down with file encryption and everything. And then the final step, they're inviting Anthropic or OpenAI to slurp up all of their data. Sup freaks. Before we get into the show, I just want to send a heartfelt thank you.
(00:39) Thank you for joining us and ask for one quick thing. Could you like this episode? Subscribe to the channel and if you like the conversation, join us in the comments section. Wild Times, brother. Great to be here with you. >> Great to be on again. Thanks. >> This is take two. And as I was saying in take one, I've been asked to uh intro my guests better for the new uh the new TFTC freaks who have joined us.
(01:00) We're we're blowing up. The show's growing. It's incredible. And for any of you new >> audience members out there, I'm sitting down with Mark Zuman, co-founder of Maple AI. He is at the cutting edge of AI privacy which is a topic that I think is becoming more and more on top of people's minds as they begin to experiment with the tools that are hitting the market particularly the agentic tools and they're realizing how much access they're giving over to some of these large language models particularly provided by open AI and
(01:35) tropic in Google and so I figured it'd be a good a good day, good week to get an update from Mark because I think we are I don't want to say we're at like this inflection point where we're going to go one direction or the other. Um I'm actually pretty optimistic because of individuals like yourself and uh the team over there at Maple with you and Tony Anthony, excuse me, um building your tools.
(02:02) So maybe maybe an update for the freaks who didn't catch our last or who did catch our last episode um where we talked about uh what you guys are building at Maple and how you're incorporating it. What what has happened in the last 6 8 months since we last met. >> Yeah. Uh sure. Thanks for the intro. Uh man, it's not what's happened the last 6 months, it's like what's happened in the last 6 days.
(02:24) Everything is changing so fast. It feels like a whirlwind trying to keep up with the AI news. So, uh, I guess for your listeners, if if they feel overwhelmed by this, like I I share your your sentiment. Um, a lot has happened. I mean, Maple has grown a ton. We've added in live web search, so now it's not stuck in the past, but it can grab current information.
(02:46) Um, but it doesn't do it like in a in a it does it in a in a private uh way where we use the Brave Search API, we protect your identity, all that kind of stuff to go out to the web and fetch information for you. And then um back in like December time frame, we really started leaning into this Aentic AI stuff and wanted to put an agent inside of Maple and do some kind of chat assistant within Maple.
(03:08) And then at the same time, obviously, other people had the same idea. So this whole open claw thing jumped on the scene. Um we'd been looking at it and then they came on and so we're like, okay, this this kind of validated this idea. People really want to have some kind of AI that's like constantly working for them.
(03:23) So we're we're building that in the Maple, not OpenClaw itself, but similar functionality. Um, what else do we have? We've got really powerful reasoning models now. So Kimmy K2.5 is like on par with a lot of these anthropic, a lot of these open AI models. So you get really good intelligence, you get really good agentic coding, um, math computation.
(03:45) There's all sorts of great things that are in there now. And the open source models have caught up. Like it's it's indisputable now. they are as good as the frontier labs. And so we uh we need to stop thinking that like using using open source models is like a subpar experience. Um we just need to build better tooling around them to make them even even more competitive.
(04:06) I think that's key, the tooling. Somebody's been using Open Claw for um a while now in AI terms. Um, it's insane how beneficial it has been to our workflows and extending my product productivity here, but I'm always acutely aware of what's happening behind the scenes. Um, I've got mine living in a VPS. Don't it doesn't have control of my computer or anything. That is for a reason.
(04:33) It's cuz I know that the sort of walled garden model providers um have access to everything I'm doing when I'm when I'm painting their models. And so I think you are far better suited than I am to basically explain what's happening cuz I think a lot of people are out there experimenting with open claw connecting it to bod's API uh open AI's API and just running wild.
(04:59) What what is happening when people are are doing this and running wild behind the scenes? >> Yeah. Uh you're effectively giving some kind of computer software full access to your computer. or even some app access to everything on your computer to run programs, to read files. Um, it's it really is like a virus.
(05:21) Back in the 90s and 2000s, we were like so nervous about viruses on our computers that we would install McAfee anti virus software or Norton or whatever they were to block these kinds of things. And now we're like welcoming them onto our system. And uh but they behave the same way, but this time we are, you know, inviting it in and we feel like we can control it.
(05:42) Uh so I would just say like remember that as you're installing this stuff, you're giving it like full root access to everything that you have, which uh I commend you for running it in a VPS. That's a smart way to do it. Or run on a totally different computer, one that is locked away from everything.
(05:58) Um, but if you're going to put that computer on your home network on your same Wi-Fi as everything else that you're doing, uh, you might have a bad time. So, I would just be careful because this thing could start scanning the network looking for ports that are open, start walking around quietly behind the scenes and you won't quite know what's going on.
(06:16) Um, I have this uh I have this this meme constantly running in my mind. I don't know if you've seen the meme of the Simpsons where Mr. Burns and Smithers are like walking into this lockdown compound and he has to like scan his eyeballs to open up one door and then he has to do his handprint to open up another door and it's like this really secure thing and when they get to the final room there's this like back door that's just like blown open and this cat or dog comes wandering into the final enclave where he gets into and it's like
(06:42) that's how that's what everybody's doing with their uh with their open claw. They're getting a separate computer. They're locking it down with this. they're doing file encryption and everything. And then the final step is they're inviting anthropic or open AAI to slurp up all of their data. So they're just kind of leaving this whole open this back door open, if you will, to all of that.
(07:02) So just just know know what you're getting into kind of thing and be willing to only share that information that you want to have shared with with those companies. So I I assume that most people that are doing this or relative noviceses aren't aware of this and if you weren't aware before you are aware now after Mark's incredible um explanation but what are you seeing in terms of the people who are not noviceses like longtime software engineers uh system admins and programmers uh in terms of their recognition of that back door that you just described and do
(07:37) you think they are worried about it? Do you think it's okay? Do they think it's a necessary evil? Like, is there a sense amongst senior software engineers that there there needs to be a more secure setup? >> Yeah. Well, well, one, I I don't want this to be total doom or anything cuz uh this is like really fun to play with, too. Uh I'm sure you've been having fun.
(08:00) Open claw. I think you've mentioned that you stay up late at night a lot playing with it, and I definitely do, too. Um I know a lot of people are. So, there's there's tons of fun things to do. It really reminds me of the early days of the internet when we were first discovering email and discovering uh you know the worldwide web and geocities and being able to do your own HTML.
(08:18) Like it's super cool stuff. So I think people should definitely play around with it. as far as, you know, the the seasoned veterans that are playing with this, people who are like entrenched in technology. Um, I feel like they put up good guard rails and they try to put up good walls and say, "Okay, this is this is the area where I know that anything I say in here could end up getting leaked onto the internet at some point.
(08:41) " So, they use it appropriately that way. But then um most of most of the really serious people I talk to, they also have some kind of private place that they talk about stuff, whether that's Maple or a local AI. Um they have some place where they're they're like, "Okay, I'm going to separate these two worlds and I'm going to make sure that I'm protected over here and anything I say over here, I don't want it to end up online or end up getting getting sent to the government or something.
(09:07) " So, um yeah, I I don't know that some people feel like it's a foregone conclusion. I definitely hear from people like, "Oh, privacy, it was gone a long time ago. So, we don't even need to have that fight anymore." Um, but given the the amount of sales of Mac minis that have that has happened in the last month, um, I think a lot of people, a lot of like normie type people are realizing that, uh, privacy is something they still care about and that they want to try and preserve.
(09:36) >> Yeah, completely agree. And bringing this back to the tooling, like how far away do you think we are from feature par for the tooling around um more private ways of interacting with these models like Maple? >> Yeah. Uh this is one one spot where the the open source AI is still trying to catch up and that is um I mean there there's a software that they all run called VLM and the VLM software for better or for worse you know has to try and handle every single open model out there and so it doesn't do any single
(10:08) model really well and the the reason why Anthropic and OpenAI are able to operate so well and be so effective is that they write all sorts of proprietary harness software middleware that that's in between you and the AI. and can just like do really good system prompting really good tool calling all of these things and the open source AI just they need better they need need better support there.
(10:32) Um so uh for example if we wanted to make Maple the primary LLM provider inside of OpenClaw there are there are certain limitations right now with the tool calling where openclaw will say all right let me spin up a sub agent and do this thing. Sometimes it'll work really well. Other times it'll just kind of like go off and never come back.
(10:51) And so that's that's a limitation right now that we're running into. And it's not just us. It's it's a whole bunch of open source model providers that are running into that problem. Now, if you look at someone like Kimmy who creates open source AI, they have their own hosted version and they build all of this really nice middleware that makes it work better.
(11:09) But now you're trusting their hosted solution. They're a Chinese company. very likely tied in with CCP um just because of what we know of how business runs in China. Uh they it's really difficult to be in business without also having a connection with with CCP for data sharing. So uh you know that that's just something to to take into into consideration and uh something that we need to be building better in the open community.
(11:34) Is there a clear light at the end of the tunnel for building that or are anthropic uh open AI Kimmy or is that sort of middleware proprietary? It's hard to reverse engineer. >> No, I I think it's it's a classic tales all the time with open source development where it moves a little bit slower in some regards, right? In some ways, open source moves really fast because you have a million people tinkering with it and throwing it out there.
(12:04) But with something as complex as hosting software for for open models and LLMs, um, everybody's kind of centralized on this one project. And so now we're at a bit of a bottleneck trying to get that project to make improvements and move forward. So it's it's just going slow, but I think with time it'll improve and maybe someone will come out with a an open source competitor to that project and um, and we'll see some innovation there.
(12:27) But there's there is light at the end of the tunnel. I think I think improvements will be made. it's just going to take a little more time to to get them through. >> How um how do you think the next six months play out with this race between both source and open source models? >> I think we continue to have new models from open source community that that push the boundaries and we'll keep seeing this leaprogging.
(12:52) Everybody will release everybody releases and then like the next week the competitors come out with something and the next week the open source competitors come out with something. So we all benefit from that. Uh, I do love that that timeline that we're on. Six months from now, I think there will be other OpenClaw type projects.
(13:07) I don't think that OpenClaw necessarily is like the final the final Aentic project out there, especially now that it got scooped up by OpenAI. Um, that that has tainted it for some people. Um, so yeah, I I think that we're going to see a lot of just really fun innovation out there and a lot more people will be running agents, having them read their email, having them rent read their calendar, booking appointments for them, um, shopping for groceries for them, like all sorts of really cool things that that that we've been promised in this future of AI. Um,
(13:38) I think in 6 months, those are going to become tangible realities for a lot of people. >> Yeah, I can feel it. I can feel it. What um what are your thoughts? I mean, I was tweeting this out yesterday. If you look at the sort of public spat between the Department of War and Anthropic right now in the idea of AI safety, I think it's pretty clear to anybody paying attention that Anthropic uh is I don't know if they're feigning um worry about it or if they're legitimately worry, but I think the end product of them getting their way could
(14:13) be uh bad for for open- source models particularly. But it seems like the Department of War and Anthropic are a public spat. But to me, it seems like a Hegelian dialectic problem um problem reaction solution thing where Anthropic's like, "Hey, I don't want you to run wild with this. We need more guard rails.
(14:33) " >> And I could definitely see the government saying, "Okay, we'll give you guardrails. We'll create these regulations that force them onto the market." Uh do you worry about that at all? Yeah, I mean government regulation moes to drive out competitors like that's that's a classic dark pattern that happens in business when really if we want to have true um safe AI if you will or um what's the for responsible AI is a phrase people love to use right if we want to have truly responsible AI it should be trained in the open with open
(15:06) data open weights we should be able to see everything so that we can we can examine it and that's just not happening right now. So, Anthropic wants to say, "Hey, we're going to make it safe for everybody, but the government will like bless us and we'll be the the one safe place to do that.
(15:23) " Um, that's that's just not good for anyone because now we're all depending on this closed company, this closed source and depending on the government to be the the auditor of safety. And I I don't want the Department of War, Department of Defense, the US government to be the one that's telling me which AI is safe for me to use.
(15:41) Um it just seems like we're all going to have a bad time. >> Yeah, I mean the the progression of events over the last couple weeks has been um quite interesting for the tinfoil hat Marty Jones and me. You >> Yeah. What do you see in there? Well, when you pair the the sort of back and forth between Hegsth and um Daario in Anthropic and the Department of War with the announcement of this distillation attack that Anthropic was subjected to where the open source models were um Anthropic is claiming they were using Anthropics models to
(16:17) train themselves and they're they're claiming some sort of copyright infringement or an attack on their proprietary data. um and alpha uh that seemed like again going back to the problem reaction solution I think anthropics of the department of war like look we're getting attacked by these Chinese open source models we need to lock down um >> and it's especially uh especially rich when you consider the fact that it's pretty well known that Anthropic use some of those same tactics to to get their model into the state
(16:54) that it currently is Yeah, I mean they all trained on public data, copyrighted data. It's I mean it's it's obvious that they did and if you talk to any copyright holder out there, they have not been compensated for all that training that happened. So it's it's very rich for these companies now to say, "Hey, they're training on trying to steal all of our stuff.
(17:16) " Uh, I mean, may maybe maybe this will be like a foot in my mouth moment, but I also like I don't know how a partnership between Anthropic and the Department of Defense, Department of War stops these open source models from continuing to progress and develop. Um, it's it it would take it would take a really big card for them to play when it comes to like being authoritative over the technology that we use within the United States.
(17:46) And uh I don't know that they necessarily would want to play that card, but they would really have to lock things down and uh try and control what American citizens are using. Um that's that's a that's a difficult road to go down. So for this rip was brought to you by our good friends at BitKey. Bit Key is the hardware wallet that makes Bitcoin easy to use, hard to lose.
(18:06) The two or three multisig you download the mobile app, you pair it with this hardware device here. Uh, you have a key here, one on your mobile app, block holds, one in the cloud. Comes with incredible features. The newest of which is chain code delegation where you can set up your wallet and you can send and receive Bitcoin from that wallet as long as you're doing it with your hardware wallet and your mobile wallet and block is none the wiser.
(18:34) You get privacy with chain code delegation. in privacy mode. You can auto stack using Cash App, Strike, Coinbase, other apps uh directly to your BitKey wallet. Uh easy to set up. If you have friends and family that still have their Bitcoin on the exchange but need to get it off, send them to BitKey uh to pick up a bit. Go to bit.world.
(18:54) Use the code TFTC20 for 20% off your BitKey and you can buy one right here. We have one in our YouTube store. You don't have to go anywhere. Just click that link. Use the code TFC20, 20% off. Pick up a bit key. Sup freaks. This rep is brought to you by our good friends at Silent. Silent creates everyday Faraday gear that protects your hardware.
(19:11) We're in Bitcoin. We have a lot of hardware that we need to secure. Your wallet emits signals that can leave you vulnerable. You want to pick up Silence gear. Put your hardware in that. I have a tap signer right here. I got the silent card holder. Replace my wallet. I was using Ridge Wallet cuz it's secured against RFID signal jacking. Uh silent.
(19:28) The card holder does the same thing. It's much sleeker. Fits in my pocket much easier. I also have the Faraday phone sleeve which you can put a hardware wallet in. We're actually using it for our keys at the house too. There's been a lot of robberies. They have essential Faraday slings, Faraday backpacks. It's a Bitcoin company.
(19:42) They're running on a Bitcoin standard. They have a Bitcoin treasury. They accept Bitcoin via Strike. So go to slt.com/tc to get 15% off anything or simply just use the code TFTC when shopping at sltnt.com. Patented technology, special operations approved. It has free shipping as well, so go check it out. Yeah.
(20:00) Well, then you pair it too with the push for the digital ID age verification >> children. >> Yeah, >> probably come the models as well. Um the money that these these agents use, they're going to try and do ID verification there. I mean, it already happens to an extent with stable coins just on the edges. >> Mhm. >> Um so you can see the them trying to throw cold water on the proliferation of more sovereign AI tools moving forward.
(20:25) >> Yeah. I mean, you have Stripe working with Open AI, right? they they published their their payments thing. I think it's like APA or something. And then you have Stripe also working with Coinbase on X42. You've got USDC stable coin with with Circle mixed in there. So, there's all sorts of like choke points and regulation and censorship opportunities for someone who wants to control how these agents pay each other and really interact on the web.
(20:52) >> Yeah, I think I agree with you though. I don't think they'll be able to contain these things. And if they do, they'll breach containment. And >> yeah, >> as I was mentioning before we hit record, I I discussed a lot of uh similar topics. Not not a ton of overlap yet, but um I had Cali on.
(21:14) he recorded earlier this morning and it actually made me incredibly bullish because he's he's incredibly optimistic and I think mainly because of the agency these tools give the many to to fight against the few centralized entities. And so basically like giving a call to action to hey if you care about this stuff and you think you can be beneficial and and contribute to the efforts of open source projects that will preserve your sovereignty and privacy and freedom as we quickly and acceleratingly transition into this this AI uh driven world. Um you can you can
(21:50) contribute. >> Yeah. Well, and we talk a lot about privacy, but privacy really is upstream from freedom, right? Like you you have to have privacy first in order to have freedom. And so I view us as being a freedomoriented AI. We're trying to give people an alternative to the system that's being built, the system that is government partnerships and moes that are meant to control who has access.
(22:15) Uh and the open source community is like, no, we've got another option for you and we need more people building in this space. you know, we we need more people doing this because if we want to have these AIs out there that are able to fight against this closed system that is that is likely to be thrust upon us or attempted to be thrust upon us, we can have we can have like this whole wonderful world outside of that wall that operates and is difficult for them to shut down.
(22:44) And uh the way that we control it is we put it all out in the open. We let everybody inspect it. We let we let everybody build tools, build build the good AI tools, I can fight against the bad AI tools, and um we can have it out out in the open and just disinfect everything by by adding some sunlight to it all.
(23:00) Um and that that's that's where I see the open source community really having a lot of power in this struggle right now where where a lot of people are worried about AI. You know, they're worried about what it's going to do to their jobs. They're worried about what it's going to do to to how they think, to education, you name it.
(23:17) Um, people are worried about AI in pretty much every space that you go to. >> Yeah. I mean, shifting gears to building with this stuff. Um, I think we talked about this last time you were on, but again, with how quickly things are developing, I think it it does um deserve a check-in like building out Maple using the AI tools. How's that been in recent months? um building Maple itself, we still use a combination of things like Claude as well as Maple.
(23:49) Um we build out we build open source software. So um we don't mind that like our stuff is going to anthropic because it's it's ending up on GitHub and everybody's computers anyways. Um but we also use Maple a lot for our development. So we've got the the Maple API, the Maple proxy. Um we've put a lot of work into making it work with things like open code.
(24:08) So if you don't want to run cloud code, you want to run something that's more freedom oriented, you can run open code and you can have open code talking to Maple on the back end. So now everything you do there is is encrypted. Um and so I I actually use open code with Maple to do a lot of my development work for Maple itself.
(24:26) Um some of it that I do is is not just writing the code, but I actually use it to help me come up with feature specs, like you know, as a product manager type role where it's like, okay, I want to work on this really big feature within Maple. For example, we're adding we're going to add projects into Maple. A lot of people want projects and the ability to organize things into folders.
(24:42) Um, so I can totally vibe with Open Code with Maple with these open source models and help me come up with this very lengthy, very detailed feature specification that I can then hand over to a coding agent to build and and get out there inside of Maple. Um, but that whole thought process and ideation, you know, I like doing it in a way that is a little more private and and not just giving it all over to anthropic.
(25:03) Uh, that's just one example. Um, but then the the proxy itself has been super useful when I go to visit uh companies or organizations and do AI trainings with them. We can vibe code really cool powerful tools for them right there on the spot that are powered by Maple in the back end. Um, I I posted this online last week, but like I was able to build two tools really quickly uh just by texting over signal with my open claw that was that was running Maple in the background and I was able to build a tool that did translation. So, if you are like an
(25:35) activist organization or a non nonprofit and you want to publish some kind of thing and have it go out in multiple languages, then you just paste this into my tool. It runs it to Maple in the back end and comes up with 20 different language translations or however many you need within a few seconds.
(25:51) Um, and these are just like really small tools, but things that you can run locally. You don't have to send all of your stuff to to other companies. You can just run it locally and then have Maple be the the brain behind it. Um, so yeah, there there's a lot of really cool powerful things that that people are building um with with something like the Maple Proxy.
(26:10) >> It's all there. It's all possible. Yeah, I mean while you're talking about the the maple proxy and basically talking to it via signal, I think that's one thing that I've come to realize or developing a stronger belief in the idea that just the form factor of how we interact with the internet through apps is completely changing in front of us.
(26:35) Like my whole user experience of interacting with my computer has changed dramatically. um where before 2 months ago I was using voice to text but seldomly but now anytime I I need to get something done it's like voice to text to my agent to go get stuff done and then you think about what these agents can do in terms of just building stuff for you quickly whether it's decks dashboards visualizations and then you think about are apps even going to exist in the future and I know we've talked about this behind the scenes means by this idea, but the form
(27:10) factor is if agents are going to be doing a lot of the heavy lifting for things you want to get done, it's going to be somewhat invisible in the back end. These agents are just going to be speaking with each other um in speaking with services via API calls. Are you a believer in that? >> No, definitely.
(27:30) I I do think there will still be software in the world. um us as human beings, we still want to rely on other people to to figure things out for us and do the heavy lifting, do the maintenance, do the security auditing and that kind of stuff. So there there will exist that a market for that, but a lot of the small things that we depend on right now are just going to be agents figuring it out on their own.
(27:50) And it's going to be one-offs, right? They're going to spin something up. They're going to go talk to their agent. They're going to make it happen and then they'll wind it down. They won't they won't need it anymore. Won't need to persist. And if it does, it'll just persist within the agent and it'll be like, "All right, here's my own little set of tools that I built myself and um I'm going to use it to talk to these other agents out there and and maybe there will be some kind of sharing between them where they're like,
(28:11) "Okay, here are these skills that I have that I'm going to share with you, kind of like we see with with OpenClaw." Um, but they're going to be like spun up by the agents themselves. Um, do you want to hear like my my three to five year projection of like where I think some things are going? Um, >> no, I don't think anybody wants to hear that.
(28:29) >> Yeah. Yeah, right. Um, I've been working a lot right now on on two-way voice communication. So, I want to make Maple better at two-way voice. I want to take it on walks with me and really just be able to talk to it. I want to be in the car. Uh, you know, I have CarPlay up on the screen.
(28:44) I want to be able to like interact with Maple and just have a two-way conversation with it there. Um, I think 3 to 5 years from now, most people are interacting with AI just through some kind of hardware device that they're wearing. Um, I know that you and Matt have talked about this and and I think I think spot on there, but it's going to be something like AirPods or some kind of pendant you're wearing, glasses, something that has microphones, potentially cameras, um, that that's how we're going to just be like interacting with the internet now and getting things
(29:09) done. Um, with with some combination on our phone or something we can look at. The the thing that I want Maple to be ready for, and this is what this is what I I I want us building toward is that that future right there is likely going to be proprietary hardware. It's going to be things running on these devices that we cannot inspect the code.
(29:29) We don't know what they're doing. We don't know what kind of directives they have in them or or guard rails or gates that they've put up to to prevent you from doing certain things with them, right? So, I would love for Maple to be in a spot where we can support, we can create, we can be embedded on devices that have open-source firmware with reproducible builds that you can have your own headphones and you can be doing stuff and you know, okay, when the microphone's on, I know first off when it turns on and then when it is on, I
(29:59) know where it's going. I know what it's recording. I know how the data is being handled. Um, whether that's through my own infrastructure or through some kind of encrypted backend. um rather than this kind of quasi surveillance state that's going to continue to be embedded in our lives where everybody's wearing AI tech that's constantly listening and and watching everything we do.
(30:19) >> What's the landscape of that hardware and firmware looking like? >> Uh right now we have a lot of big companies that have talked about building things but we don't have any concrete plans on what they're building. Um, I mean, if if you look at if you look at what's publicly available, right? Meta has their glasses.
(30:39) Apple did the Vision Pro, which is very hefty and heavy. Um, I don't think that's where they land. And then OpenAI is openly talking about building their own device. They've been very public about that. All three of those companies um are are proprietary and locked down. And I don't see them saying, "Hey, we're going to open source our firmware and we're going to provide rep reproducible builds so people can cryptographically prove that this is the code that's running on your device without a back door inside of it." Um I'm not seeing
(31:11) anybody, well I shouldn't say not seeing anybody. There are a couple of of companies that are building open things. Um one of them that's really interested is called Pebble. I don't know if you remember the Pebble watch that kind of launched the whole smartwatch revolution. >> Um they've they've come back and they're building open source hardware both watches and they've got this ring that they're working on.
(31:31) Um to me that's really compelling and I'd like to dig into there more and see if if Maple can be something that that can partner with the device maker like that. Um I'm also bullish on daylight computer. I think that there's a lot of interesting things that could be done there um with with open firmwares and and with Maple and and other kind of private AI solutions if you will.
(31:53) Um and I think there will be others that pop up too, but we need more people building out in the open. >> Yeah. Yeah. Star 9 >> progress they're making >> is imperative. >> Are you uh are you optimistic right now? Oh yeah, totally. I am uh I mean I uh I have to sell Maple to people and convince them that they shouldn't give all their data over to the the big AI companies.
(32:23) Um so I often come across as like negative and a doomer, but man, I'm having so much fun. Like this is this is a blast. These these AI agents building with AI. Um, I mean, I know you've expressed this opinion, but it's it's very empowering, especially I I come from a software engineering background, but people who did not know how to write code, now they're able to use these tools to program and do things that they couldn't do in the past where they had to depend on other people.
(32:50) And it's like your ideas are no longer the limit. It's just which ideas you want to pursue, which kind of like, you know, sweat do you want to pour into something and trying to make an idea really take off and and what kind of market can you validate to to build something for that? Um, so I'm super optimistic about that.
(33:05) I think that this is a really fun time, a really cool time to be alive. Um, pairing that with like the difficult transition we might go through with with people getting laid off and and job markets having to transition to some kind of new industry that we don't know about yet. Um, I I'm I'm constantly like at odds with that, but I am optimistic that that we find a way through this.
(33:31) >> What do you mean by you're at odds with it? I'm at odds with the fact that like I'm really like excited and having fun building AI even though I know that there are people who are out there who are super worried that they're going to lose their job u because of the AI and I've already I've already talked to people even even family members and friends who have run into this problem and it's it's hard for me to be smiling and be like yeah isn't this awesome I'm sorry you lost your job.
(33:57) Um, so I I mean my message is like learn how to use these tools and it's not only going to make you better at your job, but it'll help you team up with other people. If a if a bunch of really smart people lost their jobs, they can team up together, form a new company and hire people who uh, you know, can come along and and I think we just birth thousands of and millions of new companies that are smaller, more nimble, um, more local, right? Um, I was chatting with something somebody yesterday who who kind of framed it this way. I thought it
(34:25) was cool that you have all like your local ranchers and your local farmers in your community. You go to the farmers market to buy stuff from them. Well, with these AI tools, uh, we we possibly come up with with all these local technology companies. So no longer are we having to look to Silicon Valley to build all of our tech that we all run on some cloud infrastructure, but instead it's like in your town, you have your local CRM provider who's building stuff that's just just great for you.
(34:53) And then if you need new features that they don't have that another town over has, they just use AI to like go vibe code that feature into the CRM that you're using in your local town. And so I think that there's a lot of really kind of cool stuff that can come out of it. Um, and we more decentralize technology down to the local level.
(35:09) >> So, freaks. When you take Bitcoin seriously, you start with custody. You want to control your keys, avoid single points of failure, and make sure your savings cannot disappear because you or someone else screwed up. That is what Unchained has been focused on since 2016. Unchained is the leader in collaborative multi custody and Bitcoin financial services that keep you in control.
(35:27) They secure over 12 billion in Bitcoin for more than 12,000 clients. That means about one out of every 200 Bitcoin sits inside an Unchained Vault. Their model is simple. You hold two keys, they hold one key. It always takes two keys to move Bitcoin, meaning their single key can't access your Bitcoin on its own.
(35:41) Just resilient shared custody that gives you institutional grade security while keeping you sovereign. Onchain also lets you trade straight from your vault. Access Bitcoin back commercial loans, open a Bitcoin IRA where you hold your own keys, and set up personal business, trust, or retirement vaults. They even offer inheritance solutions built for long-term hodlers.
(35:56) or opt for the highest level private client service with Unchained Signature and get a dedicated account manager, discounted trading fees, exclusive access to events and features, and much, much more. If you want a partner that helps you secure and grow your Bitcoin without giving up control, go to unchained.
(36:11) com and use the code TFTC10 at checkout to get 10% off your new Bitcoin multiig vault. That's TFTCT10 at unchain.com. Sup freaks, this rip was brought to you by our good friends at Salt of the Earth. It's so delicious. in my pink lemonade electrolyte mix. It's pink Himalayan salt. There's no sugar. It's way better than LMNT Liquid IV. I went through a a big electrolyte kick, testing them all out, and I let landed on this, settled on this, been drinking it pretty consistently every day for two years now. It is my favorite.
(36:45) This is the pink lemonade. They have orange here. Uh, as you can see, this one's ripped. I had this on the train ride back from New York last night. I'm always stocked up with these things. They also have creatine packets. Very convenient, particularly if you're traveling and you like to work out, you like get those brain juices flowing.
(37:00) They have these creatine packets as well. Uh they're about to launch a bunch more flavors. Lemon lime, uh watermelon, and and a few others as well. Um so go check it out. Go to drinksotay d r i n ks o t.com. Use the code TFTC for 15% off. Seriously, game changer in our house. My wife drinks it.
(37:24) I drink it or boys drink it. Stay hydrated. It's a beautiful thing. I mean, I asked this question to Cali, but I'll ask you as well because I think getting different perspectives on this for for the audience uh could be beneficial, but like what would your advice be to somebody listening to this who has been apprehensive or um intimidated to begin playing around with this stuff to to take the first step? Like what should they do? How should they approach it? What should their mindset be? I I think it's imperative, excuse me, I think it's imperative that everybody
(37:56) play around with it. You just need to try it. I know it can be scary um and maybe it feels overhyped. Um I tend to be someone who uh when something gets hyped up, I ignore it for a while because I don't want to be caught up in fads and that's that's served me pretty well throughout my life. Um but this one does not appear to be a fad.
(38:17) Um, so I would just recommend sign up for one of these tools, pay a monthly subscription because you're going to get the full access to the tool. You're not just going to get like the the free access that's limited. And then pick one thing in your life that you're like, "Okay, this is something that I do all the time.
(38:34) Maybe AI can help me do it easier." Um, and just try to try to automate that one thing. And and automate isn't necessarily like it's going to keep going for you constantly while while you're asleep or something. Doesn't have to be that difficult. um just something that you have to write an email you have to write once a week to a boss or um you know something that you do at home every every day.
(38:56) Pick one thing and see if AI can help you do it better and I think that'll be your tow hold into seeing kind of like what these tools are capable of and then you'll start coming up with more and more ideas of things that you can do. >> Yeah. Yeah. Play with it. you you'll get obsessed quickly if you you have the aha moment and you are successfully able to achieve one of those tasks um rather quickly. It's holy crap.
(39:20) I need >> Yeah. Well, and I know that I'm biased here because I sell subscriptions to AI software, but but seriously, like if you need to cancel a Netflix subscription and sign up and any one of these AI tools, just sign up for one and pay them 20 bucks a month. I don't care if it's open AI.
(39:37) I would rather it's Maple, but but pick one of them and just get off of zero. Just get started playing with it. Um and do it for a month, you know, just give up Netflix for a month. I think you can survive and try out one of these tools and see if it brings any value to your life. And I I am highly confident that you will find some kind of value in it.
(39:56) And then you can make the decision, am I getting more than $20 a month out of this? If you are, then keep it. And if you need to get some Netflix going again, then do that. But uh but I think you should just get off of zero and get started. >> For all you Christians out there, it is the Lenton season. If you haven't given up anything anything yet, maybe you drop Netflix for the rest rest of Lent and pick up a Maple subscription, begin toying around with this.
(40:20) >> There you go. >> Um back to your voice to voice. Uh cuz I I I agree. I think that's important. I think we're headed towards a a her world. I think her I think Spike Jones did a very good job of uh of visualizing what the world of AI will look like in in the form factor which most people land on.
(40:42) I think voiceto voice is where we're going. I think my voice to text stepping stone um right now is just that a stepping stone. Eventually, the voice models will get so responsive and it'll just be much easier to to correspond with your agent via voice then voice to text or text to text, whatever it may be.
(41:03) Um, but you had your you had your uh your agent join the What Bitcoin Did podcast and completely bored the system. What happened there? >> Yeah. Yeah. Um, yeah. So, I knew I was coming on with Danny. We were going to record on Sunday night my time. And so, I was like, "Oh, I've got this crazy idea. Can I get my open claw to come on and join the podcast? Um, I haven't heard of anybody doing this, so it's possible that it was a first, but I spent Saturday with uh with a Maple Proxy with Open Code and just vibe coding the heck out of this thing. I
(41:33) think I think I had Claude Code in the mix. I had multiple things going, but I built it and it's it's this really cool system. So, uh, I got it so that it could join a Riverside link uh because that's what he used to record that episode. It comes on, it's listening to all the audio. It creates like a fake audio connection to the system.
(41:51) It in it gets all the audio in and then it uses a local whisper model. So, it's not I'm not sending anything to Anthropic, by the way, or or OpenAI. It runs a local whisper model that transcribes all the audio and then it takes that text and it sends that text to Maple and says, "Hey, is this something that I should respond to or are they just talking back and forth with each other?" And then once it decides, "Oh, this is something you need to respond to.
(42:12) " Then it comes up with a response, sends it back to my agent, and then it uses another local model. It's called Supertonic, which is a a voice, a text to speech voice generation model. Creates the voice, and then it sends it back out through this fake microphone that it plugged in to Riverside. Um, and then I had it build like a video thing, too.
(42:32) So, it had it had its its profile with like these emanating rings coming out as it talked. Um, and it was able to respond to us. it uh it didn't work as well in my testing as usually happens when you do you know AI or uh technology stuff but uh it was able to listen to me and Danny and then it it heard that I was talking to it and came up with a response but in the process I don't know what happened something with the Riverside platform it booted Danny off of the the call so he was gone it was just me and my bot Cooper on what Bitcoin did and then eventually Cooper
(43:02) got booted off by Riverside too so then it was just me for a little bit until Danny could get back Yeah, first ever AI agent joining a podcast live in >> so um you know little little alpha here but I'm I'm working on can I build a show around that. So I uh I'm I'm drastically improving the software and I want to maybe create a show where me and my bot co-host a show and I bring people on just to talk about how they're building agents and what they're doing with their agents.
(43:32) So, >> right. >> First, >> I would love to join as a guest. >> Okay. >> I mean, I'm I'm a layer behind you. I'm not sure if you saw, but this morning was the first ever podcast companion edition of the Bitcoin Brief newsletter, which I've been building with my agent over the last few weeks. We've re um sort of reinvigorated the 5day a week newsletter um for the Bitcoin brief and with the help of my agent.
(44:00) But I've been doing it for the last two weeks. So I was like, "Hey, um, maybe there's some people who don't like reading too much and they'd rather listen to this." And so last night I vibe coded, I guess, for 2 hours. and was able to set up a a flow where um we'll take the sort of written newsletter, build a script, a newscast like script about it, hooked up an 11 labs API token and uh used a there's my audio is out there.
(44:31) I've been I've been recording podcast for for almost nine years now. So, >> my voice is going to be out there. I'm thinking about and I need to trademark it, I think. But um was basically able to spin up like a little podcast companion to the Bitcoin brief. And so now every morning when I sent out the newsletter, I had the Kron John set up where we had the newsletter ready and then 5 minutes after it's ready, it triggers the Bitcoin brief podcast skill which then goes builds the script, does the voice generation and publishes it to
(45:01) our our website and our RSS feed. >> Did you So did you train your own voice? Like does it sound like Marty? Yeah, >> that's awesome. >> Yeah. >> And that technology has been around for like a year and a half now, two years, and it's only gotten better. So, it's just going to continue to improve. >> Well, we tried uh we tried something on YouTube like a year year and a half ago with this, and it just sounded too robotic.
(45:23) But now, it's still a little robotic, but it sounds good enough. But >> yeah, >> point being the ability to just do these things. And as a content creator, for lack of a better term, somebody who runs a media company, it's something, as you can imagine, I've been thinking very deeply of since I've been interacting with these agents is how's this medium going to evolve and change? And I think your idea for an agent co-host for a podcast is one of the examples of things I I think many people aren't prepared of. They may have a a visceral negative
(45:56) reaction to it, but I think it's inevitable. It's going to happen. Yeah. Well, and the idea is out there. So, if somebody else does it before me, you know, free ideas are here on the internet. Um, something that you just with with your Bitcoin briefs and making your own podcast. Uh, this is one thing I love about the agents as well is they they generate so much documentation.
(46:16) They're always writing things. Um, and it can be overwhelming. It's like you're chatting with it and it's like, "Okay, I saved all those research to a file." And sometimes I read those files. Sometimes I just don't have enough time. So, I have it summarize the files for me. But where I find it really useful is like if I'm going to the gym or I know I'm going to be in the car for a little while, I'll just text my agent and be like, "Hey, can you make an audio version of that file?" And this whole podcast harness that I set up um for my agent to
(46:40) have a voice and stuff. And now it's like, "Oh, yeah. I can do that. No problem." So, it'll take that file, it'll create a 10 minute, 20 minute, however long it needs to, a little MP3 file or a wave file and send it over to me and then I just listen to it while I'm at the gym. And I've actually thought about like to make it even easier, maybe I'll just build my own private RSS feed um that I can somehow authenticate against and then I can have my agent just be dumping audio files in there and I can wake up in the morning
(47:05) and have my own personal podcast of like files that my my agent feels are important for me to listen to and I can just throw them into my podcast app and just have it kind of mixed in there with everything else and I can review stuff for work. I can review, you know, personal things that that I'm researching and uh it just it it allows it to like flow into my my productivity workflow much easier.
(47:26) >> Yeah. How how much more productive has this made you particularly with the agent stuff? >> Yeah. Uh it's uh it's hard to say right now. I should track the time better because I definitely spent a lot of time building this stuff up, but then it's made me more more productive in other ways.
(47:45) So maybe it's a wash right now, but all the time spent building out these harnesses are going to pay off in the long term. >> Yeah. Well, that's like that's been the most fascinating thing. It's like the Jeff paradox coming into play. It's like, oh, it's going to take all the jobs and like you're not going to have to work anymore.
(48:01) And I found myself working more than I than I have in in years just because it's so fun to play with. >> Yeah. >> Yeah, it's true. Well, and case in point, something that saved me time. So, when I recorded with Danny, the the audio from my bot actually didn't come through Riverside very well on his recording. So, he texted me.
(48:17) He's like, "Hey, we're we're going to publish this soon. We're trying to edit. Your bot's audio was really crappy. Do you think you could somehow re-record that?" And I just texted my bot and said, "Hey, your audio didn't come through. Do you saw the transcripts? Can you just give me a new file?" And within 90 seconds, I had two highquality files of the things that it said on the show.
(48:35) And I just texted them over to Danny. That would have taken me quite a while to like go find the transcripts and then like use software to generate the audio and then make sure the mic levels were okay and everything. Like that saved me probably 3 hours of work and it was able to do it in 90 seconds. >> It's insane. >> Yeah.
(48:54) Yeah. Like last night I was like ah we had dinner. My wife was like oh you going to bed early tonight? I was like yeah you know what I've had a productive day. I'm probably going to go go to bed at 9:30 tonight. And then at like 8:45 I had the idea for the podcast and I was up for two hours structuring everything. Wound up in bed like 11:30.
(49:11) >> Yeah. When that idea hits you're like I just got to do it right now. >> Yeah. >> Totally. >> What um I mean bring this back to Agentic Payments. I think considering this is a Bitcoin podcast. Uh >> where do you think this goes? Um obviously at Calon we were talking about using eCash for agentic payments and obviously it has privacy and um through open protocol benefits compared to stable coins and whatever Visa, Mastercard and Stripe are working on.
(49:41) But it I think that's one one thing that many Bitcoiners myself included naively thought in the beginning. It's like oh the agents will just choose Bitcoin because it's the best money. it's the native uh digital native internet currency that that they'll end up on. But I think we're still in a state where um these agents need a lot of direction and will take direction from the humans um controlling them uh for lack of a better term and they don't have a preference yet for this. But how do you see this playing
(50:14) out? Yeah, I I think we're running into the same problem that we have in meat space right now, which is if I want to pay with Bitcoin at a local merchant, most of them don't accept it. And so using Bitcoin as money in real life has become difficult because we have a merchant, you know, availability problem.
(50:33) And we're going to we're seeing that online. If even if agents were told go pay with Bitcoin, there aren't many services that they could go pay for using Bitcoin. But you can rest assured that given all the deals going on between Stripe and others that those merchants will accept stable coin agentic payments. Um because that's that's who's going to start accepting it first.
(50:58) So it is definitely not a foregone conclusion that that they're going to choose Bitcoin as the best money. We need to be building it. We need to be getting online merchants to accept it and we need to build tools that make it super easy. Right? They're not going to accept it if it's not convenient. So we need to be build convenient tools that can be um plugged in.
(51:17) Um Zapright if you're listening to this, hey Zapright, we need uh we need some good good aentic payment functionality. Um I know that Lightning Labs is working on it. I know Amboss is working on stuff like that. Uh Albi has been working on it. We need everybody kind of working on trying to solve this. Cali of course is is working on stuff too.
(51:36) Um we need good tooling and then we need merchants to accept it. Um, there's there's a third way. And I think the third way that maybe we run into is if if you give your agent a directive to go buy something for you and it gets blocked out by the traditional system. Um, I think maybe maybe one example would be um, you know, ammunition for a gun.
(51:58) So, if you are a competitive shooter and you you you know you compete legally in shooting competitions and you tell your agent, "Watch my inventory of ammo and go buy more before I have upcoming competitions. Here's my calendar. Make sure I'm always stocked up with my favorite ammo." if if for some reason that gets blocked by Stripe because Stripe has notoriously blocked those kinds of transactions, um your agent's going to have a bad time, but it's going to want to solve things for you.
(52:24) And so it's going to search the internet for an ammo provider that accepts Bitcoin. And if one isn't there, it's going to come back to you and say, "Hey, here are all these providers. This is where I want to buy it, but they can't accept it." And maybe it reaches out to them for you. Maybe you reach out. But eventually there will be someone and I'm pretty sure there are some there's I know there's at least one ammo provider that's a Bitcoiner, right? >> Phoenix and ammunition.
(52:44) >> Yes. Yes. So if they're willing to accept Bitcoin then they're going to have all the agents coming to buy ammo from them. And so this is actually one way that I see merchant adoption potentially is when people get blocked out of the system um and then maybe it grows from there. I just don't think we should depend on that.
(53:01) I think we should be more proactive and get ahead of the problem. >> Yeah. Yeah, that's the uh again and to your point the chicken and egg problem of I had somebody on the show a couple weeks ago and they were saying it's a demand uh a supply side problem. It's like no the supply of Bitcoiners are willing to spell spend Bitcoin um is certainly there and particularly they want the ease of giving their agent a budget and having it go complete things for them autonomously using Bitcoin if they need to pay for stuff.
(53:34) It's a demand side problem on the merchants. Like the merchants need to demand Bitcoin. And it's something we've been banging their heads uh in the Bitcoin space about for well over a decade now. The merchant adoption meme has been around since Roger Ver. And uh yeah, I don't know what it is. Maybe it's the interchange fees.
(53:53) Maybe it's the I really like what the money devkit guys are doing where you can have your agent accepting and sending payments within 5 minutes. like is it like KYC AML onboarding friction that pushes people towards Bitcoin? I don't know. >> Yeah, that's something I need to look at more. Money devkit, I I'll be honest. I I know.
(54:12) Um I mean, we've talked to Nick Laney before, but I need to look into that project more because I think that's really cool. I like the I like what I hear about it. >> Yeah. What um I must apologize for being late. I want to get that on air on the record. It was I was tardy to this to this. >> Everyone knows now they do. But I want to be respectful of your time.
(54:32) Um, I know you're extremely busy. What um what have we discussed that you think is something that that the audience should know um and care about right now? >> Um I mean we uh Maple is Maple's here to to build the the freedom future for AI. So um we would love for people to partner with us.
(54:58) We have actually quite a few organizations and companies that are starting to buy team accounts on Maple, which is super helpful for us because not only are they securing their entire pipeline, but it it helps us to bring more uh stabilization to our platform, you know, more revenue coming in and helps us to build up better tooling for them so that they have better it's this chicken and egg problem where it's like we want to have business customers but we need better business features and vice versa.
(55:25) Um, so if you are an organization out there, if you're like a small firm or a small company, even if you're at a large company, but you have your own organization within that large company, I would definitely encourage people to go check out tryaple.ai and check out our teams plan because that that's really um I think it's just really helpful for the cause in general.
(55:43) And then um yeah, we talked about it briefly earlier, but we're building out this AI AI assistant within Maple. So it's it's going to be very different from like the AI chat that you have now. When you start a new chat in Maple or Chatd or anywhere, you pretty much start with nothing.
(55:59) Like there's there's no understanding. You open up and it's like a blank slate. It doesn't know anything about you and you have to like tell it everything you want it to know. That functioning will remain within Maple. But now we're going to have this very conversational, easy to talk to chatbot that is going to give you short responses just like you and a friend are texting each other.
(56:16) And it's going to build up really good memory about you over time. So, it's going to get to know you and it's going to be able to kind of help you out more than having to start from zero. Um, and this I think is really where the privacy is like is a a big win. And this is something that OpenAI and others don't have.
(56:33) And that is when you are talking to a tool that you know is end encrypted, you're much more open about things you want to talk about, you're much more willing to give away information because you know that it's safe and protected. And that is where the most private AI can now become the most personal AI.
(56:48) and you can have this AI chatbot assistant, your own personal assistant, executive assistant, whatever you want to call it, that's going to get to know you so well that it's going to become so much more useful to you than a tool put out by some big company that you don't totally trust because you're not being as open with it. Um, so that's coming.
(57:05) We're working on it right now within Maple. It's going to be here in the weeks and months ahead. Um, and we're we're really excited about that. It's such a massive unlock for the agentic world. Like just having sort of cache context that I can pull from easily. That's the one thing I've learned with Open Claw is just setting up the memory system and making it so it can pull things from memory rather trivially.
(57:28) I mean, that's the big problem with just using the models by themselves is the memory compacts, the context compacts every so often once you hit the token limits. Now with these harnesses like openclaw when you guys are building a maple it's going to make it the user experience goes up dramatically. >> Mhm. Yeah.
(57:47) And then at some point you end up with so many agents you like kind of forget to check on them. I I kind of run into this where I'll have multiple open codes running at one time um in different tabs in the terminal and it's like oh shoot I forgot to check on this one. It's just been sitting there waiting for me to confirm something.
(58:01) Um there's this there's this cool tool with with one of the plebs on on Noster. Um it's called Wingman. Uh you can go check it on GitHub, but uh it's this cool way to open source code to manage all of your agents and you can like do it from your phone, you can do it from a web browser and you can basically like keep tabs on them and make sure that they're continuing to move forward on things that you want.
(58:21) Um so I need to go I need to go look at that more. He uh he just made me aware of it yesterday. Um so yeah, I think there's some some cool additional tooling to build around these things to make you even more effective. >> Yeah. And I guess uh one other piece of advice I would give to people out there, don't get too emotionally attached to your uh to your agent.
(58:42) Um I think uh getting oneshotted by AI psychosis is a is a is a very real um possibility out there. >> It's a tool that gets stuff done for you. It's not a it's not Scarlett Johansson and her. >> Yep. You can give it a name. You can give it an avatar, but please just remember it's a tool. Uh, and don't Yeah. Don't go further than that.
(59:07) >> Yeah. >> I mean, hey, free world. You can do what you want, but I think you're gonna have a bad time. >> Yeah. >> Well, Mark, uh, thank you for doing this again on short notice and for putting up with my tardiness. I think um no as I said every time you come on the show I think what you and Anthony are building is extremely important and I'm very happy to see the progress that you guys have made and fact that you guys are on the tip of the spear of um this AI revolution particularly on the the side of freedom and and privacy
(59:40) as it develops because uh like we've said many times uh throughout your appearances on this show could be very dystopian if we don't do this the right Yeah, definitely. Well, thanks for having me on. It's always fun to catch up and chat about this. >> Go to tryaple.ai. Use the code TFTC. You'll get you'll get you'll get uh you'll get >> 10% off >> 10% off your subscription.
(1:00:03) Go check it out. >> Peace and love, freaks. Awesome, man. >> Thank you for listening to this episode of TFTC. If you've made it this far, I imagine you got some value out of the episode. If so, please share it far and wide with your friends and family. We're looking to get the word out there. Also, wherever you're listening, whether that's YouTube, Apple, Spotify, make sure you like and subscribe to the show.
(1:00:29) And if you can leave a rating on the podcasting platforms, that goes a long way. Last but not least, if you want to get these episodes a day early and add free, make sure you download the Fountain podcasting app. You can go to fountain.fm to find that. $5 a month get you every episode a day early. ad free helps the show, gives you incredible value.
(1:00:53) So, please consider subscribing via fountain as well. Thank you for your time and until next time.
