Who can actually max out 5 AI subscriptions?

It's crazy to me to hear people be like, I got five different subscriptions, and I maxed them all out. Like, that feels performative to me. I mean, I could understand maxing out one or even two, honestly, but

maxing out more than that, it feels crazy. Like, what do you Yeah. There's... People have, like, 20. I I see this all the time on Twitter, but, like, I have 20 different subs, and I've maxed them all out. Like, what are you building? It's cheaper than not paying for pnpm employee. It's like, well, okay. But Wes are you... What do you need? Like Show us. Show us the amazing things that you're building. I don't see anything other than you do yapping on Twitter.

Welcome to Syntax. Wes got a potluck episode for you today. What should you be doing? While your agent is working? How do you stand out? Is is blogging dead? How do you keep your agent on the rails? How much should your employer cover for token spend? How do I get my engineers interested in using AI? And finally, a non AI Wes, what are you using for emails? If you have a question, make sure you send it to us. Go to syntax.fm and click on the potluck button, submit your question, and we will answer it in an upcoming episode. Also, we wanna tell you, San Francisco, we are coming to do a syntax meetup on October 27 at Bear Bottle Brewing. So if you are anywhere near San Francisco or you wanna, dare I say, hop on a plane, train, automobile, and come down to San Francisco to hang out with us, we are going to be hosting a meetup. October 27, Go to syntax.fm/meetup to grab your ticket. It's free, but you do need a ticket to get in. We'll see you there. First question from Alex says, what's the modern day equivalent to blogging? I thought this was a really cool question. A few years ago, writing about technical things was a way to get noticed, showcase your skills, and maybe land a job as a developer or product designer. I feel like people don't read blogs as much anymore. What has taken its place? TikTok, Instagram videos, and what do you actually talk about? Are people still interested in seeing someone share their technical knowledge? I'm a product designer, and I used to build front end prototypes. These days, I mostly work with cloud to make them. I really enjoy the field and what I do, and I'm not looking for a way out, but I don't wanna get lost in a sea of people doing the exact same thing. I want to stay relevant. So long story short, how do we promote ourselves? Now this is a great question because we even saw Wes when Jeff got announced, there was a couple people being like, we we built this. And it just didn't have the, like, hilarious Twitter video to to get posted with. And as frustrating as it is, it's not enough to simply just, like, build something and and put it out there, or share anything. That used to be it. That was that was awesome. Right? You you work really hard on something. You learn a lot about a specific topic, and then you can write a blog post, and people will love to hear about that. And now there is just 10,000 times the amount of content out there that's hard to just get, people's attention. And I think, like, there's also... A lot of this content is really good, and people like to watch stuff that are... Is well presented and and entertaining and and whatnot. So, how do you per per...

Sorry. I was gonna say that again. So how do you promote yourself right now? Right now, it seems to be that people are looking for opinions. Right? There's just so much stuff out there, and people are looking for somebody who has taken the time to figure something out and has garnered some opinion on on these new pieces of technology.

They have experience with it. Maybe they've done some exploration.

Often, the stuff that is most interesting to me is somebody who has been interested in a specific aspect, and they have not just done the, like, high level six prompts and and make a demo. They've actually gone into it and used their noggin about how should we best approach this thing. What what might it look like if we were to design with our voice? You know? There's all these, like, people that are on the next level of, like, how do we use this stuff to do something that is not just build the same stuff that we've always done just faster. You know? And and for those people who are able to distill their thoughts, cohesively and and do it in a interesting manner, I think that those are the people that can promote themselves.

The mediums, I I still think... Like, blog posts are still a great way. You're not gonna get the crazy, like, million views, but, like, Hacker News is still mostly just text, and and those are are the things that are landing on on Hacker News. Obviously, posting to social media is very good as well.

The, like, short form video is its own thing altogether as well, but it's certainly not a bad way to practice being able to say, I am passionate about this thing. I learned about x, y, and z. I have opinions on this thing.

Figuring out how to distill that down into a slightly entertaining sixty second video, it's it's not not a bad skill to have in in going forward.

Yeah. Yeah. I think in general, yapping is the new blog. Yeah. Logging. Yeah.

Although, you know, I... There's a lot of yappers out there, and I think the thing is is that, like, people are... There's always, as you mentioned, room for somebody who knows what they're talking about and communicate it Wes. Where...

What we end up getting instead is, like, 1,000 awful YouTube channels being like, this changes everything with a bunch of, just bad or dumb opinions or not informed, just racing to get something out, which is always frustrating to see. Right? When you... I I remember being really frustrated trying to find any good information about Hermes because every single YouTube video about Hermes with some AI bro who doesn't know JS, Node gonna say is ask from his elbow. Is that a, is that a say? That's it. You got it. That's... Yes.

Got it. I never I never said that before. Who just trying to get clicks and views and whatever. So, you know, there's always gonna be room for people who know what they're they're talking about Yeah. And who can do it well. Yeah.

It used to be also, like, we would just say, like, hey. Build stuff and push it to your GitHub because when people go looking to hire somebody Yeah. They're going to see that you have stuff on your GitHub and you know what you're talking about, and it's not just the same to do list that you... Everybody did when they were learning Rails.

And that's a little bit different now because Yeah. Everybody can push a whole bunch of slop to their GitHub, and it's really hard to go through that. But if if if I was looking to hire somebody and they had some, like, neatly worded blog posts or just, like, little investigations into... Like, I'm following this guy right now on Twitter. He works for Netflix, and he's rebuilding the micro duck right now and the hugging face micro duck. And he's just sharing little bits of information about what he's learned, little things that he's run into.

And it's just just photos and and just being like, oh, I had had trouble with x, y, and z. And, like, if I was looking to hire a really smart guy, that guy would probably be at top of my list right Node. And and he's not doing, like, some influencer social media. I think that's a totally different game. He's just, like, sharing interesting stuff and able to communicate it in in a neat way. In this case, it's just text and photos on Twitter. So And that's a lot harder to

AI fake. Like Totally. You... YouTube videos, easy to AI fake. Blog posts are like, who's who's actually writing good blog posts anymore by hand. Right? Like, the blog post that I read, I take one look at them. I read a paragraph, and I'm like, alright. I'm done. This JS, like, this is junk. So... Yeah. Yeah. Yeah. I agree. That kind of stuff that is connectable, that is human, that is relatable, that is, you know, real.

Exactly. Exactly. So just I think we could sum that up with just, like, do interesting stuff, put it out there for people to to to see. It's not going to, like, go super Vercel. But I think if if it is that you're you're trying to stay relevant and have opinions on all of the stuff that is changing right now, I think that that will stand out significantly when it comes to employer looking at, does this person know what they're talking about? Totally. Alright. Next one here from Elias.

While an AI agent runs for minutes at a time, do you two actually get up, or do you sit and watch it? I write with Claude Node all day, and I Node I never move during those weights. So I wrote a hook that prints one stretch line into the session while an agent is still working. It's not a timer. It counts only the minutes an agent turn kept me waiting. So a day of quick turns never fires it, and stepping away for forty five minutes clears the count. You both take training seriously.

Yes. We do.

So I'm curious what you do instead of total time. Tool... The tool is open source if anyone find it useful, and they have a link to it called Vibe Stretch.

I love stretching during working.

What I do typically while one agent is working is I put another agent on a different task, and then I have another agent on another task, and then I have another agent on another task.

And, by the time one finishes, another one has, started, and you just kinda go into a loop until your brain fries. But, yes, what what should you be doing? Man, it would be... Like, it would probably be good to do push ups or get the blood moving or go for a walk or... Yeah. Yeah. Man, like, that's a great question. Like, what should you be doing while your agent is is churning? And I will... Well, before you get into that, Wes, I will say I don't have agents running for that long, typically. If an agent for me is running for, like, ten minutes, I'm getting kind of annoyed. I like to have a a tighter loop than that, and that's a meeting. Yeah. But even even if you're waiting for, like, two or three minutes, that's enough to sort of break your context. And that's why everyone's talking about

their flow getting... Like, you don't get into that flow state anymore.

What I've been trying to do is rather than just go, like, go on Twitter or whatever, JS just, like, take a look at what it is that you're building and and think about, what could possibly be done. There's so much specifically in the UI of your applications Wes you can tell an agent, hey. We're building x, y, and z, but there's so much more time needs to be spent on, like, writing down and detailing what needs to be fixed with your UI application. So what I was doing last week is that I set up one, like, orchestrator agent. I set up another one, which I just call my, like, GitHub issue one, and this is just a very cheap, model that is running. And the orchestrator will just, like, peg off the GitHub. It'll it'll take a take a GitHub issue, work on that one. And then as that's being worked, I'll go into the the GitHub issue one and say, hey.

I'll just sort of just, like, brain dump everything that is wrong with the application at at the current state. You know? When I click on an item, I shouldn't be able to drag and drop it. You know, I was building a a three d, gym builder. I'll I'll show you a demo of it in a in a coming episode.

But there was just, like, so much around what the UI looks like in all of these little things. And and quite honestly, it took longer for me to, like, figure out these things, think how we should better approach this, research what are the design patterns around this, and then, distill that down into a GitHub issue. It takes longer than... To do that than it is to, like, have a single turn in it. So as the agent is turning, try and figure... Take a look at your application and whether it's what you're working on right now or whether it's something else, unrelated.

And and try to to document in detail all of the problems that you have so that when it does come time to to pick up that issue, you have this huge backlog of information rather than just you just saying, like, make the UI better, more modern. You know? Do a bit of research.

Yeah. Yeah. People who don't do a lot of AI coding, or they use it in in still, like, an autocomplete type of way might think, like, that's crazy, this conversation in general. Like, oh, I I see every line that it writes or whatever. But the way that we write software with AI is different than how you wrote it before because, again, you are chiseling away at a statue that is gotten close the first time, and then you're refining and then you're refining and you're refining rather than building something up from the ground up. Right? So, that process requires that I and that intent to refine. Right? So I like your point about being able to spend that time, like, using that time to understand what needs refining and to review and those types of things.

And if you want to see all of the errors in your application, you'll want to check out Sentry at century.io/syntax.

You can sign up today and get two months for free. Century is just a really incredible tool for not only tracking your performance, making sure application has no bugs, but even just seeing what goes wrong when something goes wrong because things go wrong all the time when we're coding. And you don't want a production application out there that, well, you have no visibility into in case something is blowing up, and you might not even know it. So head on to reduce entry dot I o forward slash syntax. Again, we've been using this tool for a long time, and it totally rules. Alright.

Anonimo says, how do companies handle employee AI usage? An employee at home working on their own dime may only do a couple of prompts, and ex... Expect an outcome. However, the same employee at work with near infinite company budget may prompt and prompt and prompt until they do something that feel is close to perfect.

I feel this would cost the company a boatload of money. Do companies give each employee an AI budget? Great thing. And I think we have seen in the last six months, a lot of companies change their stance on this. Yes.

It was initially...

Everyone's like, doesn't matter. Like, just... Like, this is a magic box. We can do everything. And and then the spend got a lot out of control, and, like, the slop Sanity that people were shooting off started getting overwhelming. And and the problem starts to be how much it costs and how much it... Like, somebody has to review all of this code and and security issues, all of that type of stuff. So I did ask on Twitter, how much does your employer cover for AI usage? Do you get subs, budget, unlimited? Handful of people, unlimited.

Couple people said they will give us $200 for a sub. Some people say that $500.

A lot of people that are on, like, enterprise.

The enterprise for a lot of these big things, Anthropic and Cloud, they they bill based on token. So the... It's it's not as good of a deal as the, like, $200 a month sub. Some people said they get several subs, so people get covered, like, $500 a month, and they'll use that to buy a codex and a cloud sub. And they'll they'll use one and and run that out and then use use the next one.

Seems to be all over the place, but the overwhelming majority of them seems to be around the 2 to $500 a month thing. And I I think this is something that people have to...

At least right now, people have to learn to use, which JS, like, you have these resources available. You can't just willy nilly run up. Like, I... You could very easily spend, like, a thousand dollars a day as a dev if you are building lots of new features and constantly scanning everything. So it's it's a bit of a skill as to, like, how to appropriately budget this type of thing. Whether this will be a problem in six months from now has... Has to be seen. But for right now, I think most people are are getting, like, a $600, $500, $200 a month. And then the

employee is... It's left up to the employee to figure things out. Yeah. Because what you just rip with, API token based anything, and next thing you know, the, the HR is using,

Fable 5.1 to draft an email and just spend Yeah. Is getting crazy. You know? I mean That's just the people that don't realize how much it costs. Yarn you set up, like, a Yeah. Like, a a reminder and, like, to check your email every two minutes and, like, all of a sudden, that's $10,000 a day?

Yeah. Normies do not understand the cost. They're like, oh, I got a chat GPT subscription at home or whatever. It just works, and it's done. Right? Mhmm.

But, yeah, when you're going token based, it's crazy. I think it's up to you to to understand also, like, it's it's good for you to learn how much this stuff Scott. And if I do choose a cheaper model, what does the output look like? You know? Like, just like we had to learn how our performance works in our applications and how to write code efficiently.

I think, at least right now, a skill you need to have is how do I take these resources and get the most out of it? Because, certainly, a lot of these people with these... I got a couple of DMs from people with, like, $15,000 a month. They get access to this type of thing, And you can go absolutely nuts. And if if you have, like, a leaderboard inside of your company showing who ESLint the most tokens, people are just gonna be churning these and creating all sites with unnecessary features. So I think there's some restraint that can be had in these things, and a good way to practice that restraint is by a, somewhat of a limited budget and with the ability to then scale up if you need to. You know? Like, if you're like, hey, Bos. We're rewriting in Rust. I need $20

of tokens. You know? Like, that that could possibly be a way to get additional help. How would you be like, a token approval, like, approval token budget for a specific thing rather than just yellowing all the time. Right? Like... Yeah. I'm sure we'll see way more of that JS companies try to figure out what the heck to even do. Yeah. I will say, though, that the

the $200 a month subs is is by far the... If you look at how many tokens you use Easily the best. Yeah. If you take a look at, like, the token... I use this app on my on my Mac called Node Bar, and I hook up all of my subscriptions

to it. Right? I've got It's just co... It's called Node Bos, but it works with all of them. Yeah. It's from the, like, Cloudbot guy.

But it has, like, codecs... I've got codecs, Claude, Cursor, Gemini, Copilot, and z a I. Right? Those are those are all all subs I have right now. And Yeah.

It says in the last week, I've used 1,100 worth of tokens.

And and that's not even including stuff that's not on on other computers or in remote sandboxes as well. Right? And I'm certainly have not paid $1,100.

So those...

These $200 subs you can get from these are by far the best deal right now. Yes. Absolutely. Totally.

If your company's paying for one of those, get it.

That's what I'm gonna say about that because they do last... I I... When I... It's crazy to me to hear people be like, I got five different subscriptions, and I maxed them all out. Like, that feels performative to me. Like, because... I mean, I can understand maxing out one or even two, honestly, but

maxing out more than that, it feels Yeah. There's... People have, like, 20. I I see this all the time on Twitter, but, like, I have 20 different subs, and I've maxed them all out. Like, what are you building? It's cheaper than not paying for an employee. It's like, okay. But Wes are you... What do you need? Like... Show us. Show us the the amazing things that you're building. I don't see anything other than you Deno yapping on Twitter.

Yeah. Right. Yeah. That's what they're building. They're building a a a Twitter yap farm. That's that's right.

Maybe the app that you're working on Wes you, like, show all of your projects.

Like, before you delete a project from your computer, it should show you how many tokens you spent on it. And, like, this is a dumb idea.

Yeah.

Shame. Are you sure you want to remove, $54 worth of shame here? Okay.

Okay. Next question from a Cosman. How do you code the emails in your application sends in twenty twenty six? Like password reset, welcome ones, how do you just go with whatever your... Do you go with whatever your framework provides, or do you go down the rabbit hole of rolling your own HTML email? So, I've always rolled my own unless I'm using something like pocket Bos that has things built into it. You Node, I I I don't feel like this... Especially in the age of of agents, this becomes very easy, to do. But transitional or transactional email is one of those things I hate paying for. It's... It feels way more expensive than it should be to have an app that sends an email once in every while.

I've been using resend lately, but I do find it's like... I don't know why I'm paying so much for it. How do you feel about that? What do you use, Wes?

I use React render to string.

Yeah. And Right. It it works great because, like, you just... Like, emails Yarn are not that complicated. The support in them is pretty good. And and all you need is some sort of templating engine where you can make reusable components. Right? React is really good for that. And then you need some way to render that to HTML, which all of these frameworks have. And then you also need some way to, like, inline your CSS because, that's how you get the best, thing. So you take your CSS, and it will figure out what applies to what, and and you can put it in there. I know there are lots of other things out there.

Like, I know it's a React email from the resend folks as well.

I have never used resend mostly because I don't wanna use something that is specific to one company. You know? Like, a lot of these solutions that people Well, I use resend for sending. I don't use their React stuff. Okay. It just... Do you use SMTP, or do you use their APIs?

I use their APIs. Yeah. You're right. That... Yeah. That is still using their stuff. Yeah. Yeah. Like, just use SMTP,

and then use any SMTP. You Node? SendGrid is is probably a good one that a lot of people recommend.

And then so too expensive. They... What's too expensive? Sending emails?

Yeah. Yeah. How much does SendGrid cost? Let's see. You know, I was using...

Or I am... What am I using? Twilio? Twilio Node. Twilio owns SendGrid now.

I I miss, what was I using? Mailchimp's Node, Mandrill. I was using that for a while. But even then, it's, like, not that cheap. I, like, want something that's dirt cheap. That's what I want. I want something that's free. Something that I don't gotta pay for. You can't. Oh, that's how you get it thrown into the spam box. I'm on... I'm still on Postmark. I have been for, like, ten years. They switched recently from

buying credits, which I loved, because if you send a whole bunch of email at once, you just pay for that. And then if you if you have, like, a little bit of a lull in between sending them, then you're not paying for anything.

And software JS service doesn't like that because they like you to pay a monthly fee and get a certain amount of sends and all this Bos. So I'm still on Postmark just because of the pain in the butt that it is to set set up sending emails.

But I know that I could switch. It does seem like it is free for a 100 emails a month.

So side projects with low volume, which is something that I'm

often needing email for. Yep. I would probably say go get hooked up with Amazon AWS or what is the Wes because then you just pay by the email. And then if you do need some of these other features like open tracking and and whatnot, you can you can swap over pretty pretty Sanity. But always, always, always go based on standard APIs.

No matter how nice some of these features might be and whatever, it's so much better just to use basic email. So if something happens or all of a sudden your emails start getting caught in SpamBox, you can move over to another provider.

Have you used Cloudflare's send emails?

No. I have not. Actually, that is something that I need to to try out. It's one of their newer products. Yeah. As we're talking about this, I'm thinking,

wait. I did see that they do have email routing SMTP.

You can use any Node mailer or anything. Like Yep.

Yeah.

Okay. You know? Yeah. I'm I'm listening to Cloudflare.

Time to talk about deliver... Deliverability.

A lot of people are very sensitive to switching these types of things because all of a sudden, 2% of your things are now getting caught in spam. Like, that's a big cost because now those people are not buying your product. So people are... People spend a lot a lot of money. That's why Resend is such a big company. This Yeah. Email in people's inboxes is... You can make a lot of money doing that. Word.

Miles Dyson says, I overhear interviews in my office, and they're always asking candidates how to make sure that agents can't go off the rails. I'm not sure people asking the question know the answer themselves.

Sign of the times. What do you guys think? How would you answer this in an interview, and can it actually be done reliably? I put this one in here because I know Scott has lots of opinions on making things deterministic or having rules and tools in place so that things can't go off the rails. Right?

Yeah. Yeah. So, you know, I, one thing that people don't realize is that their harness often has, possibly things like hooks. Like, Claude Node has hooks that can deterministically step in if your agent is about to do something like RM. Right? I mean, there's also Deno lists and things like that to prevent your your, your AI from doing stuff. But just to use a very simple example that everyone can understand for a hook, You can say, is this agent trying to do an RM? Then provide this response to the agent and block it. Say, you can't do this. Do this instead. And that works for any type of time you want to steer an agent to do something when it's about to do something else. As far as controlling them, though, there is only so much you you can do, and you just set up the agent rules and, linters and whatnot. Right? There's there's, like, you wanna put things out of the hands of the agent and and say, okay. If you're doing this, go into this path. If you're doing this, go into this path. I use something called swamp club to deterministically route a bunch of things, and I really like that for that. That's not going to, like, keep you safe, but it is going to give the agent a guaranteed path to say, oh, like, here's a perfect instance for why Swamp Club is great. The other day, I had my jelly fin go down, and I wasn't sure why. So I go to my agent. Hey. My jelly fin's down. Can you check it out? And the agent goes off and does all this stuff, and it spins up a new copy of Jellyfin on a... In the docker that I didn't ask it to do, obviously. And that's the exact type of thing where it's like, it totally went off the rails, not what I asked for it to do. So instead, what I did is I put in a warp automation for checking the status of my existing jelly fin, where it lives, and all that stuff. So now in agencies, oh, it's asking about jelly fin. Let me hit that automation.

The automation returns a status. It then knows what to do... Like a status and instructions, and it knows what to do next. Right? And it takes it from a flow of being like, oh, let me let me start from scratch to let me have a a more guided pathway into doing things. So I I use that quite a bit for all kinds of stuff that I wanna be able to keep it on the rails more, whether that is, like, orchestrating, like, steps this, then this, then this. But there's still times when the agents can do whatever the hell it wants. So, that's why people like CJ have recommended putting things in isolation, putting... Containerizing and then running your agents in a container. They can only do so much harm there in in some sense.

And then, like, it's not practical. I mean, in addition Yeah. Yeah.

In addition to, like like, going off the rails and and causing harm, I think this question JS also asking just, like, how do we make sure that it... It's... It develops the things that we want and doesn't start, like, adding a whole bunch of stuff? And and, partially, you can do that in, like, your agents.m d. You know? Like, don't write fallbacks for absolutely everything. That's one thing that happens all the time to me right now is you change something halfway through on your second prompt, and it's like, well, we must support the original use case forever.

And it just does six if statements in there everywhere. So, like, partially, that can be done in your agents. Md. Partially, that can be done with deterministic tools, where you... Like, linters and tests. Like, one of them I wrote the other day, which was when I was working on some three d stuff, which is a whole bunch of tests that will spin up an agent browser to check the frame rate of rendering. Because very easily, you can just add features all day long, but that can really start to lag down the UI.

And every time they implemented a feature, it would spin up an agent browser and then run the frames per second and make sure that we're still getting over, like, a 55 frames a second during that. And and those are the types of things that you can do. But, also, if you find that it is going off the rails a little bit too much, that's that's probably on you, and you need to be a little bit closer to these types of things. And you're maybe just YOLO ing the prompts a bit too much. Yeah. I do. I do. I'll watch the output and be like... And I see it getting into paths that I doesn't need to be getting into, and I'll spam that escape button and be like, you asshole. What are you doing? I didn't tell you to do that.

Talking about the Escape, this is totally totally a a different Wes, but just like like steering in general.

I use all of the harnesses, and sometimes Wes you send, like, no. Don't do that, or you wanna, like, tell it to do something Mhmm. You have to hit, like, escape and just kill the whole thing.

Some of them... Like, the Node will send, like, the command the next turn. So it'll, like, it'll wait until it comes back and then grab your next message. Some of them will wait until you're totally done, and then it sends it and it's Scott kinda backtrack and you gotta hit x on it.

I found that I like the codex. I don't like the open code implementation. There there really is no steering, and I know people are like, you shouldn't do steering at all. But there's so many times where I'm just like, I wanna quickly add in a little bit of information. I know Claude also has, like, the by the way where you can ask questions or it will then tell the main harness to update something. Do you have any any thoughts on the best steering approach?

I don't know. I I don't think that's something that I figured out really well. I don't really love the by the way kind of features and stuff like that. There's a Yeah. A by the way feature in a lot of these that, again, it's just, like, kind of adding additional steering. Sometimes that that turn takes too long. Typically, when I'm stepping in with some additional information, it's, like, urgent. Otherwise, I'm not stepping in. So I almost always default to stopping regardless.

I think the one that I don't stop and then type is, Claude. I I do let that one pick it up. For for some reason, I found that Claude Node does a really nice job of that in particular, but I don't mind just hitting stop on that bad boy because it's like

So many times of, like, I just, like, I don't wanna stop it because it's working.

Yeah. And I don't wanna have to restart everything, and it's not important to stop it because it's not doing anything bad. But, like, the next turn you have, which is probably in the next twenty, thirty seconds, you should throw this message in there as well for some additional context, and maybe you wanna change course or, I guess, steer yourself. So I've... I also have not been super happy with any of them, but I do think Node is my favorite so far.

Yeah. Folks, what are you doing for that? Are you using by the way? Are you just steering and waiting for it to to pick it up? What what do you what do you like to do, to keep that going? Because, I'm I'm looking to optimize here. I'm interested in that. Yes. Alright. Next question from Ash. I'm the head of an engineering at a small Scott up. General interest in agentic development is on the lower end from my engineers.

So it's mostly me experimenting and trying to get folks to try things. How can I get my engineers more interested on their own? Would love highly engaged culture around this stuff. Wes, Ash. You know what? It's gonna be tough for some people because they have, like, an ideological, like, anger towards, integrating this stuff. Right? They don't want to do it. Mhmm.

But I I think a lot of people too who have put up a huge wall into agentic coding, like, I'm not gonna do it. It's not me. Whatever.

I don't think they've realized the progression of the models and how good they've gotten.

So I I don't Node. Like, is a demo look at what my agent can do gonna work?

Because I think a lot of these people have I I think those, like, look Node prompt things hurt more than they they actually help. Right. Yeah. They hurt.

Right.

So, like, having someone shadow you, I I really don't know if you're the head of engineering at a small Scott up. To me, it seems like like more lunch and learn type of deals where you can show off some of your workflows and how it's improving your your workflow and how it's improving your development flow and how it's making your code better or this or that would be better than, like, yes. Look at this crazy stuff I can do.

But, again, it... It's gonna be I I feel like this is almost more of a person problem. Right? Like a... How how do you relate to the people that you are working with to get them to understand the benefit to them without triggering their wall that they have most likely built up?

I I think as you as head of engineering, the, like, the top engineering needs to be constantly sharing how they are using this tool to help them.

And because they probably have... They're blinded by, like, oh, look at the one prompt. I can do x, y, and z. Whereas, like like, even inside Century, there's a Slack channel where just, like, everybody is either asking questions about, like, how should we do this, or a lot of, like, the top engineering talent are giving their opinions. And a lot of that is is critical of it, and then a lot of it is is really good stuff as well. So think that's a great... If you have a company Slack or company communication channel, having some regular means of, like, sharing things that you've learned there, I think that's a a a good idea to get in front of people. Because I do... I love the century one. Yeah. It's it's great. And even just like a screen recording, like, I don't think enough people are showing how they are working with this type of stuff.

And just... It... I I know that type of videos don't do super Wes, but if you could just internally in your company share, hey. Here JS my process.

I have this bug. I'm working on it. Here JS what I'm here is what I'm doing, and you can show the benefits at the other end.

Yes. Yes. Totally.

Question from Andrews says, hi, Sanity. How long do you think we will take to move on from using notification channels like Telegram as a primary control for non coding AI agents? Looking at Hermes desktop and OpenClaw two point o looks like web u i's or disguised as desktop apps. Is that where we are headed, or are dedicated devices like the Node Scott built? The lack of purpose built ways to interact with a... AI agents is one of the reasons I haven't fully adopted them yet. Other one being the amount of bloat that's being added automatic... Automatically, which is why building your own thing is fun, especially when optimizing for smaller local LLMs. I think everybody is trying to figure this out right now JS what is the golden goose of UIs to be able to interact with it. Right? We saw, Node has merged with ChatGPT, and it is simply just one app. Everybody's building these just, like, super apps.

We're starting to see the two big ones right now, Grokbot and Muse from Facebook, which are much more targeted at. Like, these are not for coding. These are just for your your daily tasks, and those ones are much more JS, like, a chat application. You know? But then there's there's not too many knobs that you can turn. That seems to be getting the the normies built into it. I do agree that the, like, the simple Telegram chat back and forth is probably not it because you do need a little bit more control over the UI of these types of things, but not too much where it it becomes very overwhelming because...

And I think that's why both Grokbot and Muse have been, like, very heavy on... They don't show thinking trails. They don't show tool calls. Yeah. They're just they're just showing, like, chat bubbles, like you're doing iMessage with a friend. So I think there's probably somewhere in between those things where it's a casual chat but has a couple knobs where you can adjust some settings. And I think that that will be the winner for a lot of these normies, coming on to use this type of stuff.

Yeah. The totally custom stuff is great because it can do whatever you want. But let me tell you, mine breaks all the gosh darn time, and, the missus is not happy about that. I think I get a message once a week. The AI is not working again.

So it's, it's something that if you're going custom, yeah, certainly, like, there's some really great stuff you can do there. But, again, you're... You might be running into situations where you have some janky software comparatively. So, yeah, there's a lot of other people have built custom ones if you're using OpenClaw or Hermes or whatever. There's a ton of people who have built custom ones. And, honestly, the Hermes desktop app is really good. I don't know if I would put it in front of my wife, but it... It's good.

So, yeah, that's where I'm at with this. I still have my custom one, but it is kind of annoying. Next one here is from diabetic codes. Hey, gents. I know you've answered the should I still learn to code in the world of AI question a million times about masking it a bit differently. Having been in the industry since 2014 and stepping away for two years during the framework boom, I felt like I've been fighting an uphill battle ever since. Diabetic Node, you're in luck because no one cares about the framework war anymore.

Now in a world of AI, despite having a drive to be a proficient developer, I've worked to two jobs that use AI daily. I'd struggle between taking time on tasks to learn the code Bos and using AI to get tickets done faster. Additionally, where I used to enjoy digging into learning something new in programming every weekend, I now find my drive depleted. I don't want to touch a computer.

What's a good way to stay motivated when you aren't motivated? I'm a very disciplined person with fitness, health, and life, but this is one thing I feel I can't find ideas to sink my teeth into and Node out with excitement and curiosity. All the best. Yes. This is tough. You know? I I actually struggle with this a lot too where the... It... It's like it's like playing a game with Game Genie. I don't know if you had, you didn't have video games, did you, Wes? I don't know Node you had video games wise. Yeah. The, like, Nintendo, but not much of a video game guy.

My neighbor did. I'm I'm very familiar with the Game Genie. Yes. So Game Genie made the games

fun for about five minutes, maybe that. You give Mario some super jump, and then you're... You... You're like, okay. But this makes the game easy. Right? This is no longer challenging.

And the the losing part of the challenging a bit of coding where you're digging into, like, concepts and ideas, and you're using your brain in deep ways instead of Node you're just like, oh, agent fix this. Oh, what's wrong agent? Okay. Agent fix that. Right? You're getting into a different flow where that that lack of real challenge in that sort of way can really negatively impact.

But, also, there's a number of other reasons why AI coding is more exhausting, whether or not it's just like the the the breaking of flow or various things that we heard from people, when we did our AI mental health survey. There... There's so much here.

So how do you find the excitement and curiosity? To me, I've found the joy in understanding problems at a different layer.

A layer of strategy, a layer of, like, deep refinement in UI, a layer of of understanding, like, bigger problems and structures and architectures and things because you can tell the AI coding to agent to do this or that, whatever.

And there's times when the agent's gonna pick a a really dumb idea to do something. So, like, really, for me, it's like I've had to find that joy in solving problems in a different way, in challenging myself to solve these problems in a more efficient way, to improve my process, to improve my harness, my skills, these types of things, digging more into that kind of stuff Wes the code, becomes a result of the improvement of my process rather than an improvement of the code by my hands directly.

I agree. Well put.

Thank you. Tim Apple says, not a Wes, but a suggestion. I think Wes mentioned never having restarted his computer so much as he is now when he's running AI. I've created a shortcut on my Mac to kill all running node processes and close all running programs. This seems to have helped manage the rogue AI agents on my computer.

That's not a bad idea.

There's a lot of stuff running on my computer that is node Bos. Right? Like, my Stream Deck right now. And if I kill all node processes I have in the past, then the Stream Deck stops working.

And, ideally, that thing would just restart itself, but it's not not the case all the time. But it it... This certainly is a problem that will need solving, which is spinning up all these rogue processes, and they're just... They're they're headless Node, and they're running forever. You don't know where they are, and they're just churning using up CPU cycles. Like, my battery on my computer, it... Given... It's old, but it... You could tell that there's stuff running because it doesn't last nearly as long as it used to. I used to be able to get, like, like, fourteen hours from it, and I I got, like, an hour and a half the other day. Yeah. I know. I I need better...

You know what? I I did really like Orca.

So Orca is like an app that you can run agents and stuff in, kind of like t three code or any of these things.

And the one thing I really liked about Orca is there's a resource manager built into it that shows how many megs and stuff or even occasionally gigs of CPU and RAM your agents are using, all of them. So when you're running a whole bunch of agents, you can see so clearly just how much that stuff is using. And then if you were to run your dev process and stuff through there, I'm sure it would too. I I don't I don't like giving my... Like, I don't know. Yeah. I have some stuff with that. But, I I think just Wes we... It's easy to lose sight on all of the the process that gets spun up, and restarting your computer definitely more important than ever. But I I guess I just, in general, need a better way to deal with that than right now what I'm doing, which is doing what you're doing and just deleting things. As as you notice it getting pressure or restarting, which Yeah. Since I'm running beta software on here, I I feel like restarting is probably not a bad idea anyways. Alright. Last question here we have from b Murph. I work for a company that has invested a lot of time and resources into building our own personal internal harness that's its top cloud code and implements a ton of custom skills and agents. In my opinion, it just stinks. Yeah. It sounds a little iffy.

It's a token hog, probably caching, runs slow, runs agents that don't make sense for the given problem, and a slew of other issues. I understand the impulse to build a lot of rigor around people using more and more AI, but I feel as though this approach is sort of wrong.

Now for my actual question, is this insane harness what we should be investing time and energy into, or is sort of the smaller custom agent per problem with humans as the main orchestration the way to go. In my experience, I have much more success giving my AI small problems, and I'm just quite dubious about the Yolo harness. Am I too skeptical, a hater, or in the right ballpark? Hey. I think harness is a tough problem, and harness experts, I think, are there for a reason. There's a lot of harness challenges. You don't wanna break caching.

You wanna have things being routed efficiently if there's model routing involved. You wanna make sure that everything is in the place and working the way it needs to be to have an efficient harness. What I prefer instead of a custom harness, because you know me. I'm the type of guy that likes to roll my own stuff. I've never considered rolling my own harness because I just don't feel like that's mine. That's not that's not for me. That said, I think custom tooling around a harness certainly makes sense rather than the harness itself.

So I I think I think there is a layer of your company creating something to... Around a harness that makes sense, but creating the harness itself doesn't make too much sense to me. So I think that the answer is somewhere in between your idea of, like, okay, humans as the main orchestration and smaller agents per... You know, like, I'm gonna take care of this full control over this versus the custom harness. I think the answer is somewhere in the middle. I think I think you did a little bit of they went left, you went right. I think the answer is somewhere in the middle, sadly.

I I also think that all of the stuff we've learned over the last eight months, so much of it doesn't even matter anymore. I was thinking the other day about, like, contact 7 for docs. Do we need that anymore? I don't I don't know that we need that anymore because it's just so good at searching the Internet and finding the stuff that we want. You know? Like, I I haven't I haven't been running that in a while.

And I gave it a library to do three d rendering for me, and I had tried that about a year ago, and it just... It couldn't even make, like, a box before the whole thing fell over. And now it's like... It is amazing. It's like rendering full three d printable stuff. So if you've put a whole bunch of stuff into your own custom harness, you know, you made your own g stack, Maybe it's time to, like, say which are the pieces that are actually helping us here and which are the pieces that are just making it slow and token hungry. Because even all... A lot of these skills people have installed, they're just adding unnecessary token churn and unnecessary, like, ways to just spend money. It's it's... I've... I even find that with the agent browser. I have to turn it off sometimes because it just wants to take screenshots of everything, and it's it's making everything slow. Fill my drive with screenshots.

Yes.

Yeah. Awesome. Sick. Let's do, sick picks and shameless plugs. If you Node the show, sick picks are just stuff that we've been, enjoying lately. Could be anything, Wes. I'm gonna be picking a video game, which I I like video games I play on my Steam Deck mostly, so that's typically where where I'm playing my video games these days. I got a new a new game, which is called driving rogue, which is a rogue like driving game. People describe it JS, like, what if Bellatro was a car game, which, like, car, not card because Bellatro is a card game, which on the surface, that kinda turns me off a little bit because there's so many, like, what if Bellatro was blank games, lately because, you know, Bellatro JS, like, one of those really cool games. But, again, like, the the the reward loop of it, I feel like, is a little manipulative.

So driving Rogue actually has, like, skill involved where you have to be good at driving the car and doing the stuff, and then there's Rogue like elements where you have these quick races that are improving your car. It's got a really dope art style.

At very first, I was like, yeah. This feels like I don't need rogue like things in my driving game, but I gotta say I've been playing it a bit, and it was cheap, like, $9 when I got it. Could be $10 by now. Who knows? I gotta say I've been really enjoying it and having a great time with it. So if you... That type of thing seems like in your Q Node, check it out. I I actually think it's been really, really cool. So

Sick. Alright. I have a sick pick, and it is the AmazonBasics battery screwdriver.

This thing is awesome. I've been wanting to get a battery powered screwdriver, which is...

I know that's that's what a drill is. Right? But I've been wanting to get something just for disassembling for the longest time. And I finally Yeah. I watched a video on a YouTube channel called Torque Test Channel. And what he does is he reviews all the, like... He buys, like, the impact driver from every one of these tool brands, and he'll actually, like, test out how much it costs and, the torque on it and if if if it breaks, etcetera, etcetera. And he did one on these little electric battery powered screwdrivers.

And I was shocked that the number one, by far, was not like DeWalt or Milwaukee or Skill or anything like that. It was the AmazonBasics electric screwdriver, and this thing is fantastic because Really? Yeah. It's, like, good enough to, like, break free Scott of, like, nuts. It's it's good enough if you, like, wanna, like, screw directly into, like, a piece of wood.

I was surprised. I was like, those things probably aren't that good. You know? They probably, like, came out, and you can't can't do any real work with them. But, man, oh, man. I... And it was, like, $15 or something crazy like that. Like, the the battery in here alone is worth, like, $8, and I was very surprised at how good this thing was. It comes with a couple bits and whatnot, and I do wanna get some of the, like... It it takes, like, the quarter inch bits, which is not for, like, electronics and, like, like, small stuff.

So I do wanna either buy another one that's more for, like, smaller electronics or just buy some adapter bits that will help me. But just for around the house, like, one example is Wes hang stuff up all the time, and I use these amazing, like, metal screws that go into the drywall, and then you and you screw into that.

And I used to have to get a drill, drill a little hole, and then by hand, crank that in, and then screw into it. I can just... I can put those straight into the drywall. No drilling or anything. All I need to hang something up now is just this tiny little thing, which I love.

Cool. Yeah. Check it out. Amazon basics. I'm always using my drill and having it set to have too much torque.

Oh, yeah. For dumb things. You can adjust the torque on here as Wes. So you Node. If you don't wanna overdo things, but I just... I let it rip.

Okay. Sick.

Okay. Cool. Well, that's all I got.

Anything else, Wes? That's it. Thanks, sir, for tuning.