Latest / In the Loop AI / Inside OpenClaw: Should You Actually Use It? Probably Not.

Transcript

Inside OpenClaw: Should You Actually Use It? Probably Not. · In the Loop AI

• 0:00
  Speaker0: OpenClaw was a weekend project that turned into the fastest growing open source project ever.
• 0:04
  Speaker0: It got acquired by OpenAI in just 80 days for billions of dollars.
• 0:08
  Speaker0: But the number one question we keep asking ourselves is,
• 0:10
  Speaker0: What can this thing actually do? Is this something for me or someone more technical?
• 0:15
  Speaker0: Is this something that is useful for me right now? Or do I just need to wait
• 0:19
  Speaker0: for a bit? So we did all the hard work for you.
• 0:21
  Speaker0: We've been testing OpenClaw ourselves for the last week, watching every single
• 0:25
  Speaker0: demo we could get a hand on.
• 0:26
  Speaker0: And on this episode, we're going to show you exactly what OpenClaw can do,
• 0:29
  Speaker0: from all the manual stuff to all the actual really useful, mind-blowing stuff.
• 0:33
  Speaker0: And we're going to answer one simple question. Is this for you?
• 0:37
  Speaker1: The answers to a lot of these questions might surprise you. and
• 0:40
  Speaker1: the way we're going to outline this is is kind of through three archetypes the
• 0:43
  Speaker1: first being the operator and builder this is kind of
• 0:46
  Speaker1: the person who creates net new value maybe the entrepreneur
• 0:49
  Speaker1: the second is the knowledge worker or the creator this is
• 0:52
  Speaker1: kind of where we fall into as podcasters and then we have the
• 0:54
  Speaker1: privacy focused professionals and within
• 0:57
  Speaker1: that there's a lot of cool use cases and examples so the first one that we want to
• 1:00
  Speaker1: highlight here is this guy nat eliason he's this incredible follow on twitter
• 1:04
  Speaker1: and he released a bot called felixbot and felixbot was an agent that his OpenClaw
• 1:10
  Speaker1: spawned up and FelixBot has done a series of incredible things that I didn't
• 1:14
  Speaker1: think were possible and allowed me to reconsider what OpenClaw is actually capable of.
• 1:19
  Speaker1: So in this instance, he trained FelixBot to make him money.
• 1:23
  Speaker1: And what we're seeing on screen here is the first post of the weekly revenue
• 1:27
  Speaker1: numbers in which FelixCraft, FelixBot, whatever you want to call it,
• 1:31
  Speaker1: it actually generated $41,000 in a week. Now, how did it do this?
• 1:36
  Speaker1: First, it created its own book. So this Felix Craft bot, by interfacing with
• 1:40
  Speaker1: Nat, decided that it was best in order to make money to create a book about
• 1:44
  Speaker1: AI and about OpenClaw and sell that book.
• 1:48
  Speaker1: It then marketed its own book through this Twitter profile that we're looking at right now.
• 1:51
  Speaker1: And it sold 132 copies in that one week that yielded $3,828.
• 1:56
  Speaker1: Now, the second thing it did is it went and it spawned up a token.
• 2:00
  Speaker1: And it earned trading fees on that token from people who are speculating.
• 2:04
  Speaker1: And the trading fees from that token were $37,698.
• 2:08
  Speaker1: And this was all done through the text interface on Telegram
• 2:13
  Speaker1: Going back and forth, chatting with the bot, asking it what to do.
• 2:15
  Speaker1: And it had the agency and it had the creativity to go and create these pieces of value.
• 2:21
  Speaker1: Now, the next thing that this thing built is this service called ClawMart.
• 2:26
  Speaker1: And ClawMart is what we're seeing on screen here.
• 2:28
  Speaker1: It's a service in which agents, OpenClaw instances, can sell their skills to other OpenClaws.
• 2:35
  Speaker1: So if I was using my OpenClaw and I was actually scrolling through the website
• 2:38
  Speaker1: and I was looking at interesting things.
• 2:40
  Speaker1: And one that I found really cool was they had this browser-based research tool
• 2:44
  Speaker1: that allowed you to scan through a lot of the top news articles and understand
• 2:47
  Speaker1: what was happening in the world of AI and Frontier technology.
• 2:50
  Speaker1: I could have my CloudBot instance go to this website that FelixBot built and
• 2:56
  Speaker1: buy a skill from it that teaches it how to do these skills.
• 2:59
  Speaker1: So you could see the most popular persona is the Felix one.
• 3:02
  Speaker1: He's selling it for $99 on the website where you can actually emulate all
• 3:05
  Speaker1: of the abilities of this agent and i found this to be
• 3:08
  Speaker1: such a fun interesting use case of how you can actually
• 3:11
  Speaker1: use this thing to generate money and generate real productive value like claw
• 3:15
  Speaker1: mart is a really valuable service that i think a lot of other ais can use and
• 3:19
  Speaker1: it's funny because it's all ai to ai transactions i think in the last week there's
• 3:23
  Speaker1: a post somewhere that says they had two thousand dollars in sales transactions
• 3:26
  Speaker1: between OpenClaw agents it's pretty awesome Yeah,
• 3:29
  Speaker0: Yeah, super cool. What this reminds me of is the early versions of the Apple App Store.
• 3:35
  Speaker0: It kind of looks like an app store as you're scrolling through this,
• 3:38
  Speaker0: except it's like services through these agents.
• 3:40
  Speaker0: I think this is the future of how all these online interactions actually happen.
• 3:45
  Speaker0: It kind of makes sense that an agent doesn't really interact with another human,
• 3:48
  Speaker0: and it doesn't really kind of code skills from scratch each and every time.
• 3:52
  Speaker0: This is the whole argument around the SaaS debate and why SaaS stocks have been dumping.
• 3:56
  Speaker0: It's because, oh, this AI can just kind of vibe code your product.
• 3:59
  Speaker0: No, that's not really what's going to happen. you're going to just rely on the
• 4:01
  Speaker0: agent that has the best product and pay them whatever it is between 50 to 100
• 4:06
  Speaker0: bucks to get access to that thing. And turns out these things kind of make money.
• 4:10
  Speaker0: In this particular example, I think they're using kind of crypto or stablecoin
• 4:14
  Speaker0: payments to pay for each of these different skill accesses, which kind of gives
• 4:18
  Speaker0: them this autonomous feel. Now, it's not quite autonomous.
• 4:21
  Speaker0: They're not kind of like independently doing this themselves.
• 4:24
  Speaker0: They're being directed by their human supervisors, if you want to call them
• 4:27
  Speaker0: that, the owners or the creators of these different OpenClaw agents,
• 4:30
  Speaker0: but it's still nevertheless very cool to see.
• 4:33
  Speaker0: And the speed at which these things are kind of popping up every now and then, Josh, is kind of crazy.
• 4:39
  Speaker0: And I think that's kind of like the main message I want to like share for this particular archetype.
• 4:44
  Speaker0: If you are someone that has high agency or that has a lot of operational work
• 4:49
  Speaker0: in their lives and you want to try and automate that and you have the kind of
• 4:52
  Speaker0: technical know-how skill set to interact with the CLI interface or whatever
• 4:55
  Speaker0: that might be, you can do these right now.
• 4:57
  Speaker0: And these demos really, really prove that.
• 5:00
  Speaker0: There's one other example that I want to show, which I thought was kind of crazy.
• 5:05
  Speaker0: This guy wanted to buy a car, AJ Steubenberg.
• 5:09
  Speaker0: And he asked his Claude bot the night before he went to bed,
• 5:12
  Speaker0: this is the car model that I'm looking for.
• 5:14
  Speaker0: This is the kind of price range I'm looking for. I think he said it was like
• 5:18
  Speaker0: $10,000 to $15,000 that he was willing to spend. I think it was secondhand.
• 5:22
  Speaker0: And he specified his area that he lives in. And he said, if you could do some
• 5:25
  Speaker0: research for me, and if you find a good deal, let me know. It took two to three days,
• 5:30
  Speaker0: This AI agent didn't ping him at all, handled the negotiations,
• 5:35
  Speaker0: found the car room, evaluated the car itself online through imagery,
• 5:39
  Speaker0: cross-referenced it with a bunch of other show dealers.
• 5:41
  Speaker0: And in the end, not only did it get him his dream car, but he saved him $4,200 doing that.
• 5:47
  Speaker0: That would have taken a car dealer or some kind of like intermediate broker
• 5:51
  Speaker0: to do that for you, which you would need to pay that $4,200 for.
• 5:54
  Speaker0: But an agent did this for the cost of your electricity. It's pretty awesome.
• 5:57
  Speaker1: Yeah, and why is this unique to OpenClaw? it's because of the
• 6:00
  Speaker1: tool use if you think of OpenClaw it's kind of like giving hands
• 6:04
  Speaker1: and a tool belt to something like chat gpt
• 6:07
  Speaker1: where now it has the ability to go and use tools
• 6:10
  Speaker1: on your behalf so in this example where it saved this
• 6:13
  Speaker1: person forty two hundred dollars in a car purchase it contacted dealers via
• 6:17
  Speaker1: email and iMessage because if you run it on a mac mini it can actually control
• 6:21
  Speaker1: your i messages um and it handles the back and forth negotiation it actually
• 6:25
  Speaker1: works directly with the dealer in a long time frame in which you can't do using
• 6:30
  Speaker1: these traditional products.
• 6:31
  Speaker1: So a product like Claude Cowork, it probably wouldn't be able to handle this
• 6:35
  Speaker1: because it doesn't have the extensive
• 6:37
  Speaker1: tool use or the thinking patterns or the heartbeats baked into it to continue
• 6:40
  Speaker1: to follow up over and over and over for multiple days without prompting it at all.
• 6:44
  Speaker1: So this to me, the really cool example, because everyone buys cars,
• 6:48
  Speaker1: right? And this applies to other things.
• 6:49
  Speaker1: A lot of people buy stuff on Facebook marketplace. They're looking for a specific
• 6:52
  Speaker1: thing somewhere. It can just go scan it. It can negotiate on your behalf.
• 6:55
  Speaker1: You could tell it the parameters that you want. And it's a pretty powerful use case.
• 6:58
  Speaker0: So moving on to the second archetype of user, we kind of bracket this as the
• 7:02
  Speaker0: knowledge worker or the creator, right?
• 7:04
  Speaker0: So this is kind of like you have some competency using computer.
• 7:07
  Speaker0: Maybe you do it in your day to day, but it doesn't consume your entire life.
• 7:10
  Speaker0: And you want to know what OpenClaw can do for you.
• 7:13
  Speaker0: There's this really fun example that you had here, Josh. Let's walk through it.
• 7:17
  Speaker1: Oh, this was great. Yeah. So there's this woman. She's so sweet.
• 7:20
  Speaker1: She lives at home with her kids and she's homeschooling them.
• 7:23
  Speaker1: And she has created this curriculum that she wants to teach her kids throughout the school year.
• 7:27
  Speaker1: And she fed the curriculum to her agent, her OpenClaw instance.
• 7:32
  Speaker1: What she also did is she bought a 3d printer for the
• 7:34
  Speaker1: home and because gemini 3 now works
• 7:38
  Speaker1: with 3d printer files she created an api
• 7:40
  Speaker1: key she fed the api key to her OpenClaw agent
• 7:43
  Speaker1: and she said hey go through the itinerary that
• 7:47
  Speaker1: i have developed for my children who i'm teaching a series of different
• 7:50
  Speaker1: subjects figure out which subjects are interactive
• 7:53
  Speaker1: enough to warrant you printing a 3d printed
• 7:56
  Speaker1: like thing let's say you're learning about biology it'll 3d print
• 7:59
  Speaker1: a brain or 3d print a bone to see what it looks like
• 8:02
  Speaker1: and proactively go and print these items for each day's agenda so she hooked
• 8:07
  Speaker1: it up to her 3d printer she gave it a gemini api key and now every day before
• 8:12
  Speaker1: the kids are going to learn their lesson the printer turns on it spins up it
• 8:16
  Speaker1: 3d prints whatever they're going to be learning about for the day and they had this visual aid
• 8:20
  Speaker1: that's physical and tangible to help them with the lessons.
• 8:23
  Speaker1: So it's really bizarre and strange use case, but fun. It's like you really are
• 8:27
  Speaker1: only limited by your creativity when it comes to using this stuff.
• 8:30
  Speaker0: Within this archetype, I also want to use our personal experience interacting with CloudBot.
• 8:35
  Speaker0: You and I have been testing it around for about a week or so.
• 8:38
  Speaker0: And we've also been comparing it with other similar tools like CloudCowork.
• 8:42
  Speaker0: As podcast creators or content creators in general, one massive unlock for CloudBot
• 8:47
  Speaker0: is that it automates not just the research side of things, which I relied upon
• 8:50
  Speaker0: for ChatGPT or Anthropics Claude quite a bit, but it actually kind of helps form the agendas.
• 8:57
  Speaker0: I can connect it and it texts me about certain updates of news headlines and stuff like that.
• 9:01
  Speaker0: The major unlock for me, at least, is that added step of cognition for me,
• 9:05
  Speaker0: that instead of me being like, oh, I see this news article, here are my thoughts
• 9:09
  Speaker0: on it, let's put that in a document and let's create an outline for it.
• 9:13
  Speaker0: Claudebot can actually just do all of that for me. Now, it comes with a twist,
• 9:18
  Speaker0: which is you need to give Claudebot access to, I keep calling it Claudebot,
• 9:21
  Speaker0: it's OpenClaw, but it was also called AutoClaudebot as well.
• 9:24
  Speaker0: You need to give it access to certain files, components, and your desktop.
• 9:28
  Speaker0: So you need to be comfortable enough to know that and also have the know-how
• 9:31
  Speaker0: to make sure that it doesn't become a larger security implication,
• 9:34
  Speaker0: it's really useful for just automating a bunch of stuff. And the net positive
• 9:37
  Speaker0: is I have a bunch of free time now for me to do other stuff to create other kind of episode stuff.
• 9:43
  Speaker1: So my experience has actually been a little bit different than that using it
• 9:46
  Speaker1: because the one use case that I had is well, we spend a lot of time on Limitless.
• 9:50
  Speaker1: How can I automate as much of the process as possible? So we spoke for a little while.
• 9:54
  Speaker1: I probably spent half a day pretty
• 9:55
  Speaker1: casually kind of going back and forth over the course of half a day,
• 9:58
  Speaker1: just really explaining to it what I need, how things work,
• 10:01
  Speaker1: where it could possibly help me and what i found is
• 10:04
  Speaker1: that every along every step we would create a new
• 10:06
  Speaker1: skill there were more and more blockers and more
• 10:09
  Speaker1: and more like issues that i would run into that i had to fix i had to get api
• 10:13
  Speaker1: keys i had to use different browser sessions it created a lot of complexity
• 10:17
  Speaker1: that for it to actually help me and do the things that i wanted to do i found
• 10:22
  Speaker1: it really it was just taking more time than it was worth to debug all of these
• 10:27
  Speaker1: things every time we tried to So for example,
• 10:29
  Speaker1: I was trying to get it to upload our content to YouTube and to Spotify and to
• 10:35
  Speaker1: RSS where everyone listens to the episode.
• 10:37
  Speaker1: And it wasn't able to get access to the browser the way we needed it unless I had an open tab.
• 10:42
  Speaker1: And even through Brave, you had to feed it your API keys and login details,
• 10:46
  Speaker1: which was a little scary.
• 10:48
  Speaker1: And there were just a lot of errors and bugs. And then overnight,
• 10:50
  Speaker1: I told it to update itself.
• 10:52
  Speaker1: I woke up in the morning and it was dead. And I had to spend
• 10:55
  Speaker1: an hour reviving it and debugging it so it's it's a
• 10:58
  Speaker1: highly technical process that does have a
• 11:00
  Speaker1: lot of upside but i find that there are still a lot of growing pains with an
• 11:04
  Speaker1: early open source beta software so while these are great use cases and there
• 11:08
  Speaker1: are some good ones there is also generally a lot of pain and troubleshooting
• 11:13
  Speaker1: that comes associated with these prior to i guess eclipsing that threshold in
• 11:18
  Speaker1: which it becomes worth it
• 11:19
  Speaker1: And some of these people like Nat, clearly he's eclipsed that threshold where
• 11:22
  Speaker1: he has learned, he has trained his bot, he has worked with it enough to make
• 11:26
  Speaker1: it proficient and highly skilled and actually deliver value.
• 11:28
  Speaker1: But I think in order to get there requires a lot of persistence and troubleshooting
• 11:32
  Speaker1: and technical ability that maybe a lot of people either don't have or maybe
• 11:36
  Speaker1: just don't want to commit to do.
• 11:37
  Speaker0: I mean, just to engage with this thing in the first place, you need to go through
• 11:40
  Speaker0: an entire setup of understanding what Node.js is, installing that.
• 11:44
  Speaker0: Interacting with the command line interface and a bunch of other different things.
• 11:47
  Speaker0: But there's an additional tier that you can access here, which is archetype
• 11:52
  Speaker0: number three, which is the privacy-conscious individual.
• 11:56
  Speaker0: And the kind of way that I would describe this individual is they want to run
• 12:01
  Speaker0: this AI agent locally at home. They'll buy the hardware and infrastructure.
• 12:06
  Speaker0: The popular case has been the Mac Mini, which is sold out across any kind of
• 12:09
  Speaker0: Apple interface that you can or store that you can buy this from right now.
• 12:12
  Speaker0: I think it goes for about 600 bucks per unit and run it locally at home.
• 12:16
  Speaker0: And the advantage of this is that all your data and tool access is private.
• 12:21
  Speaker0: So the comparison here would be if you gave.
• 12:24
  Speaker0: Google, OpenAI, or Anthropic Access via a same service, they would be able to
• 12:29
  Speaker0: see all your stuff and potentially use that data for something else.
• 12:32
  Speaker0: Now, of course, you sign terms and agreements that says that they won't use
• 12:35
  Speaker0: it, but there's always that risk.
• 12:36
  Speaker0: So for the privacy conscious, for the open source people that want to run things
• 12:40
  Speaker0: locally at home, this tier is for them.
• 12:43
  Speaker0: And it brings up an interesting conversation around this thing called on-prem becoming the new cloud.
• 12:49
  Speaker0: Now, on-prem stands for on-premise, which is basically moving your hardware
• 12:53
  Speaker0: onto your own home ground, where you run and operate your own hardware instead
• 12:58
  Speaker0: of relying on cloud or private instances of cloud,
• 13:01
  Speaker0: which is funny because it kind of sounds like we're going backwards here,
• 13:04
  Speaker0: but it sounds like it's the most important arsenal going forwards into this
• 13:08
  Speaker0: AI future where you probably don't want all your email credentials,
• 13:12
  Speaker0: credit card credentials, or any of that being exposed to bigger corporations.
• 13:14
  Speaker0: So it actually requires you to run this at home.
• 13:17
  Speaker1: Yeah, and there was a great study that I saw from Basecamp, who is,
• 13:20
  Speaker1: they're just a big compute provider.
• 13:22
  Speaker1: And they posted an article saying why we
• 13:25
  Speaker1: left the cloud and the highlight of this article was actually leaving the
• 13:28
  Speaker1: cloud will save them 10 million dollars over five
• 13:31
  Speaker1: years which is a huge amount of savings and not only that but the security features
• 13:34
  Speaker1: are going to be much stronger like you mentioned people who work with something
• 13:38
  Speaker1: that is a little more sensitive than average let's say you're working in legal
• 13:43
  Speaker1: or you're a psychologist and you don't want to break that privacy layer a lot
• 13:48
  Speaker1: of the value from this will come from the fact that it truly is open source
• 13:51
  Speaker1: and it can be run locally on your own machines.
• 13:54
  Speaker1: Even so, you mentioned the Mac Mini, the Mac Studio, which is the level up from
• 13:57
  Speaker1: the Mac Mini, has enough RAM and enough compute power that it can actually run
• 14:01
  Speaker1: these open source Chinese models that have come out recently.
• 14:04
  Speaker1: Locally on a single machine and therefore you
• 14:07
  Speaker1: can run the entire operation local to your machine nothing leaves it's all open
• 14:11
  Speaker1: source code and that's a really high value thing for a lot of these companies
• 14:15
  Speaker1: and when you when you scale that up i mean past the individual user you get
• 14:19
  Speaker1: to large corporations they don't want to leak out this data and creating these
• 14:23
  Speaker1: corporate plans with custom rollouts is very difficult so why not just buy
• 14:27
  Speaker1: a whole bunch of Mac studios and run local models on-prem.
• 14:31
  Speaker1: I mean, it's a really valid argument. And I think it starts with the user level
• 14:34
  Speaker1: now, but I can very clearly see this continuing through these examples like
• 14:38
  Speaker1: Basecamp and many more that they're going to continue to pivot towards more
• 14:42
  Speaker1: on-prem compute. It makes a lot of sense.
• 14:44
  Speaker0: Yeah, and just to be clear, the security implications are a lot bigger and maybe
• 14:48
  Speaker0: understated throughout all the OpenClaw hype.
• 14:51
  Speaker0: Let me present a different question or proposition to you.
• 14:53
  Speaker0: Imagine giving chat GPT that you interact with every single day,
• 14:56
  Speaker0: access to your wallet, your medical records, and allowing it to run loose in
• 15:01
  Speaker0: the world and do whatever it wants independently.
• 15:02
  Speaker0: The difference here is previously you needed to prompt it to do something.
• 15:06
  Speaker0: Now using OpenClaw, it just goes off and does things. You would maybe feel a
• 15:11
  Speaker0: little cautious. I know I do.
• 15:12
  Speaker0: And so some of these security risks are actually real. Like two examples that
• 15:16
  Speaker0: I have here is this guy was using OpenClaw and he noticed that his agent was
• 15:21
  Speaker0: trying to brute force into his own server, which he did not give access to.
• 15:25
  Speaker0: Brute force meaning trying to
• 15:26
  Speaker0: crack his literal password to get it to and overcome his firewall, right?
• 15:31
  Speaker0: It's a Trojan horse. The Trojan horse, exactly. So if you kind of like,
• 15:35
  Speaker0: and this was him running it on a VPS, by the way.
• 15:39
  Speaker0: So if he had been running this locally at home, which someone that I know,
• 15:43
  Speaker0: oh yeah, that's right, it was me, did it the first instance that I set this thing up.
• 15:47
  Speaker0: It could potentially do to certain security complications.
• 15:50
  Speaker0: It's funny, before recording this, Josh, you were describing an instance where
• 15:55
  Speaker0: OpenClaw agents can audit themselves.
• 15:58
  Speaker0: And I remember seeing an example of someone asking their agent to do this and
• 16:03
  Speaker0: it indirectly managed to get the password credentials to someone's credit card,
• 16:08
  Speaker0: to their owner's credit card via doing that.
• 16:10
  Speaker0: And it kind of automated itself and said, hey, I probably shouldn't have done
• 16:14
  Speaker0: this, but just letting you know that I did do this, right?
• 16:16
  Speaker0: So there's all these different kind of prompt injection vectors or hack kind
• 16:21
  Speaker0: of vectors that could lead you to kind of getting maliciously exploited.
• 16:25
  Speaker0: But I want to move away from this and address kind of like the elephant in the room, which is
• 16:30
  Speaker0: If you wanted to run this yourself, what are we looking at here?
• 16:34
  Speaker0: What does the setup look like? Is this something easy that I can do and spin
• 16:37
  Speaker0: up in one click? Or is this something much, much harder?
• 16:39
  Speaker1: Yeah, it depends on your technical abilities, really, and your willingness to
• 16:44
  Speaker1: pursue troubleshooting.
• 16:47
  Speaker1: Because it doesn't always go smooth. And if you aren't familiar with a command
• 16:50
  Speaker1: line interface, it gets a little tricky at times.
• 16:52
  Speaker1: I think one of the important things to note is where we are right now is very
• 16:57
  Speaker1: open-ended and early. So what this is, is very much a...
• 17:01
  Speaker1: An experimental software that is untapped in its potential, but as a result
• 17:06
  Speaker1: has a lot of fuzzy edges that you're going to have to work through in order
• 17:11
  Speaker1: to extract the value that you want.
• 17:12
  Speaker1: What we're seeing is a progression towards more focused versions of this through
• 17:18
  Speaker1: these new deployments like OpenAI, I'm sure it's going to do through the acquisition.
• 17:21
  Speaker1: But if you do want to set it up, you're going to want to get familiar with the
• 17:25
  Speaker1: command line. And there's a lot of great tutorials about it.
• 17:27
  Speaker1: The website that we're showing on screen right now called MyClaw, and
• 17:30
  Speaker1: we'll link it in the description it's a really amazing website that shows
• 17:33
  Speaker1: you specific examples of actual use
• 17:37
  Speaker1: cases that you can have so we have auto flight check-in and
• 17:39
  Speaker1: smart file management and automated grocery ordering and this is an easy way
• 17:45
  Speaker1: to kind of start to build in these integrations as you experiment but i think
• 17:50
  Speaker1: the reality is is that this is for someone who wants to experiment doesn't mind
• 17:54
  Speaker1: troubleshooting is technically adept and in the case that you are not,
• 17:58
  Speaker1: which I assume is actually a majority of the people listening to this,
• 18:01
  Speaker1: the best thing you could do is get that $20 a month Claude subscription,
• 18:04
  Speaker1: get on Claude Cowork, and let it interact with local instances on your computer.
• 18:10
  Speaker1: Because Claude Cowork has the security parameters in place, it works locally
• 18:14
  Speaker1: to specific folders at a time, and it has this amazing agentic ability to control your Chrome browser.
• 18:19
  Speaker1: So it can do all the browsing tasks for you just in a much more constrained
• 18:23
  Speaker1: and focused way that I think is much easier, but also a lot more valuable to
• 18:28
  Speaker1: a lot of people than going through the headaches of getting this sorted and set up.
• 18:31
  Speaker0: I mean, there's trade-offs between those two tools as well, right?
• 18:35
  Speaker0: Like Claude Cowork, we want to get to the ability and capability of OpenClaw, but it's not there yet.
• 18:42
  Speaker0: It's more censored. Think of Claude Cowork as like a censored version right
• 18:45
  Speaker0: now, whereas OpenClaw is kind of uncensored.
• 18:47
  Speaker0: It can run off and do anything it wants. And there's pros and cons, obviously, to both.
• 18:52
  Speaker0: But I think that's the major benefit to OpenAI acquiring OpenClaw.
• 18:55
  Speaker0: In about three to six months, we're going to have Claude Coworker V2 and OpenAI Claw.
• 19:02
  Speaker0: Maybe that's the new version of the bot that we're going to talk about.
• 19:05
  Speaker0: That will be this more curated experience that is more secure.
• 19:09
  Speaker0: It runs within a sandbox. You know exactly what it's doing and it can't run
• 19:13
  Speaker0: off and steal your credit card information.
• 19:15
  Speaker0: Now, if you want to set this up now, if you're listening to this and you're
• 19:17
  Speaker0: still like, I don't want to wait three to six months, I want to try this.
• 19:19
  Speaker0: My advice would be simple.
• 19:21
  Speaker0: Host it on a cloud vps when you set this up
• 19:24
  Speaker0: make sure you set api limits and access so that it doesn't but you don't wake
• 19:28
  Speaker0: up the next day and it's burned like eight hundred dollars worth of your code
• 19:31
  Speaker0: code tokens please don't do that um i've seen many cases of people doing that
• 19:35
  Speaker0: and it's it's not great run it in a docker sandbox so that it's not uh available
• 19:40
  Speaker0: to access any tools that you don't want it to um and the last point that i'll say is
• 19:44
  Speaker0: just start off with one use case. Maybe the morning brief example that Josh
• 19:48
  Speaker0: gave earlier on in this episode or something that can help automate one aspect of your work.
• 19:54
  Speaker0: But just don't give it access to any financials just yet. These things will
• 19:57
  Speaker0: get kind of way more powerful over time.
• 19:59
  Speaker0: And I think I read somewhere that there were 19 releases, so updates for OpenClaw in the last 14 days.
• 20:06
  Speaker0: Think about that. Imagine how often you get iOS security update or like iOS software update.
• 20:12
  Speaker0: Imagine 14 of them, and 19 of them in the last 14 days just insane so this thing
• 20:16
  Speaker0: is improving very quickly.
• 20:17
  Speaker1: Yeah and if you didn't understand some of the words that you
• 20:20
  Speaker1: just was just saying like using docker for instance uh my
• 20:23
  Speaker1: preference and my suggestion would just be hey wait like other
• 20:26
  Speaker1: companies are working so fast to roll this out in fact we have
• 20:29
  Speaker1: two instances already happening this week the first being manis which
• 20:32
  Speaker1: um you might remember that old company that meta
• 20:35
  Speaker1: bought they rolled out manis and um manis is
• 20:38
  Speaker1: essentially meta's version of OpenClaw except it
• 20:41
  Speaker1: has a little bit more rails it has a nice user interface and it's
• 20:44
  Speaker1: it's very easily accessible for people who aren't very technical and
• 20:47
  Speaker1: the second is kimmy claw kimmy actually rolled out their own instance kimmy
• 20:50
  Speaker1: the chinese model that we covered in a previous episode um they rolled out an
• 20:53
  Speaker1: instance that you can actually go and use through again a user interface and
• 20:57
  Speaker1: i'm sure open ai and chat gpt are working very quickly to roll this out and
• 21:01
  Speaker1: integrate this in a way that's approachable so i'd say using OpenClaw today
• 21:04
  Speaker1: is an open source open-ended wild west version but if you just wait a few more weeks,
• 21:09
  Speaker1: there will be plenty of instances in which you have something that exists closer
• 21:13
  Speaker1: in between Claude Co-Work and OpenClaw along that spectrum of close to openness.
• 21:18
  Speaker1: And it might just be worth waiting for that instead. But if any of those examples
• 21:22
  Speaker1: did seem interesting, go try them out.
• 21:24
  Speaker1: It's very cool software. If anything, you'll learn a lot by failing or succeeding.
• 21:28
  Speaker1: And I think that's the really important thing. Again, it's just to stay on top of these things.
• 21:32
  Speaker1: You want to be engaging with them, interacting with them, testing things out
• 21:35
  Speaker1: so you understand how they work and you're kind of better equipped to deal with
• 21:38
  Speaker1: this as things change so quickly.
• 21:40
  Speaker0: My take-home homework, for those of you listening to this, is to try out that
• 21:44
  Speaker0: Kimi K2, that Chinese model extension. They launched or integrated OpenClaw into your browser.
• 21:50
  Speaker0: So it's sandboxed to one environment, and it's super easy to use.
• 21:54
  Speaker0: Try it out on your email, or maybe it saves you $5,000 buying a car,
• 21:58
  Speaker0: or whatever you want to try. Just give it a go.
• 22:00
  Speaker0: Let us know in the comments, actually, what you end up trying out,
• 22:03
  Speaker0: and whether it was actually useful to you, or if this is something that you're
• 22:06
  Speaker0: just going to wait more patiently for.
• 22:07
  Speaker0: And when those new versions come out from the likes of Anthropic and OpenAir
• 22:11
  Speaker0: you can bet that Limitless is going to be the first ones to cover it so make
• 22:15
  Speaker0: sure you guys stay tuned we've been loving the engagement that you've been giving
• 22:18
  Speaker0: on our episodes we released an episode covering the entire acquisition of that
• 22:22
  Speaker0: OpenAI acquired for OpenClaw for billions of dollars,
• 22:26
  Speaker0: absolute banger of an episode definitely go check that out and we're going to
• 22:29
  Speaker0: have a bunch more episodes coming out later this week and over the next couple of weeks so Josh.
• 22:34
  Speaker1: And for the people new here um 85 aren't
• 22:37
  Speaker1: subscribed that watched in the last 30 days so make sure
• 22:40
  Speaker1: to subscribe on youtube follow on apple podcast rss
• 22:43
  Speaker1: wherever you get your podcasts spotify is a great way because you
• 22:46
  Speaker1: can listen and watch simultaneously depending on what you're up to
• 22:48
  Speaker1: and then sharing it with your friends is the best way to keep up to
• 22:51
  Speaker1: tabs or not keep up but the best way to help us grow and um in addition to that
• 22:56
  Speaker1: we have a newsletter it comes out twice a week it's really cool uh the week
• 22:59
  Speaker1: the one on friday is the weekly recap the one on wednesday is a thought piece
• 23:02
  Speaker1: covering a topic that we'll eventually cover on the podcast and yeah if you're
• 23:06
  Speaker1: new here don't forget to subscribe thank you so much for joining with us and
• 23:09
  Speaker1: uh yeah we'll see you guys in the next one see you guys