Peter Steinberger

Their words

The the part that's really nice about it is because I do a lot of Mac software, agents love to take over my screen and click around and if you put that in their own if you give them their own machine, it will not bother you. Otherwise, you'll fight with the agent for the mouse cursor.

Their words

I mean, honestly, that's not so much a tech problem. It's more a token problem where we could do that today, but you wouldn't get very far with your subscription and not everyone is willing to spend so many tokens.

Their words

it is always tempting to add this one feature that looks really cool but what you rarely think about is when you merge this feature it really means here's this pile of code that I don't that the person probably doesn't really understand that I don't fully understand

Their words

Now, if I do web stuff, it's easy to create a cloud session. If I do like something that requires Mac OS, that's already where like 99% of the tools fail me.

Their words

User number one should be you. And my users two to 20 were friends. So I'm sure you have some people that would actually test your stuff, but you need to be the first user. If you don't if you don't get excited of what you're building, it'll probably not make sense.

Their words

Part of it is just like you develop a little bit of a feeling how long something should take. So if I do a small tweak that should like change how dragging works and it takes three hours, I know something's wrong. I'll look closely. But otherwise, part of code review is simply like observing, looking how big it changes and trusting your gut.

Their words

So if you design call it loop, call it graph, call it workflow, it's kind of all the same. If you design something that gets a trigger or gets an input and does something for you and maybe there's a decision in the way, boom, there's your graph.

Their words

At the same time, at work, if you come to me and you you tell me this feature idea, I'm going to get mad at you. Like, it's so easy that you just discuss the feature idea with an agent, you build it, you make screenshots, you let me play with it.

Their words

And these days it's more like my sessions are topics. clearing the session sometimes even a disadvantage because there's so much information in there that helps the agent.

Their words

Every lab will sell you an agent. Open claw is the alternative. Open source runs everywhere, works with any model. And if you run local models, your data never has to leave your device.

Their words

It's hard to compete with someone who's just there having fun. Fun is velocity. The weeks I enjoyed building, the product got visibly better.

Their words

Both of those are true at the same time. A hype is like the weather. You might see it coming, but you can't control it.

Their words

So maybe write this one down. Your dependencies business model is your business model.

Their words

If you count all the permutations, you can write all the tests you want. It is impossible to cover all of these and not break things from time to time. It is infinitely harder to evolve software that has users.

Their words

You know features are the fun part. A new feature is is just a prompt away. The real cost comes after every feature we shipped of course with a configuration option because we didn't want to break everyone's setup.

Their words

Sure, they they like the abstract term of security, but in all practical terms, they updated. I broke something they depended on. I made things slower and I made things more difficult to update.

Their words

We did the the numbers and the numbers are more like 0.3%. We scanned all 67,000. We shipped the we shipped the paper. But you know a correction never travels as far as a scare.

Their words

Everything that everything you can build can be forked or cloned, but your name cannot. So your personal brand is way more important than any single product that you ever will start working on that before you need it.

Their words

But each time there was a strong emotion and the best part there were quite a few people that really wanted it and like especially to my nontechnical friends I told them no this is not yet for you and they got mad. So if that's not an indicator to have product market fit I don't know what is.

Their words

So, I, I completely moved away from that. I, I, everything, everything I blog is organic, handwritten and maybe, maybe I, I, I use AI as a fix my worse typos. But there's value in the rough parts of an actual human.

Their words

But I much rather read your broken English than your AI slob. You know, of course there's a human behind it, and yet they, they prompt it. I'd much rather read your prompt than what came out. Um, I think we're reaching a point where I value typos again.

Their words

That, that gets into the whole arch of every app is just a very slow API now, if they want or not. And that through personal agents a lot of apps will disappear.

Their words

I think the main beauty is, is that models are really good at calling Unix commands. So if you just add another CLI, that's just another Unix command in the end. And MCP is… That has to be added in training. That's not a very natural thing for the model. It requires a very specific syntax. And the biggest thing, it's not composable.

Their words

But also, I'm very excited to, like, make this into a version that I can get to a lot of people because I think this is the year of personal agents, and that's the future. And the fastest way to do that is teaming up with one of the labs.

Their words

The stuff that burned me out was mostly people stuff. I, I don't think burnout is working too much. Maybe to a degree. Everybody's different.

Their words

Like, if you think more globally, we are, we copied Google for agents. You have, like, a prompt, and, and then you have a chat interface. That, to me, very much feels like when we first created television and then people recorded radio shows on television and you saw that on TV.

Their words

Some other comparison is like, Opus is like the coworker that is a little silly sometimes, but it's really funny and you keep him around. And Codex is like the, the weirdo in the corner that you don't wanna talk to, but is reliable and gets shit done.

Their words

So, so, people who try to use like, you know, things like Gas Town or all these other orchestrators, where they wanna o- automate the whole thing, I feel if you do that, it misses style, love, that human touch. I don't think you can automate that away so quickly.

Their words

I even switched to local CI, you know, like DHH inspired where I don't care so much more about the CI on GitHub. We still have it. It's still, it still has a place, but I just run tests locally and if they work locally, I push to main.

Their words

Many times, I just do the refactor because refactors are cheap now. Even though you might break some other PRs, nothing really matters anymore.

Their words

I- i- like, we are in a stage where I'm not building the code base to be perfect for me, but I wanna build a code base that is very easy for an agent to navigate.

Their words

It's the same way as you have to play with a guitar before you can make good music. It's, it's not, oh, I, I touch it once and it just flows off. It, it's a, it's a, a skill that you have to learn like any other skill.

Their words

I know I have one blog post where I say, "I don't read the code." But if you read it more closely, I mean, I don't read the boring parts of code.

Their words

It is, it is powerful, but in many ways it's not much different than if I run cloud code with dangerously skipped permissions or codecs in YOLO mode, and every, every attending engineer that I know does that, because that's the only way how you can, you can get stuff to work.

Their words

That's why I warn in my security documentation, don't use cheap models. Don't use Haiku or a local model. Even though I, I very much love the idea that this thing could completely run local. If you use a, a very weak local model, they are very gullible. It's very easy to, to prompt inject them.

Their words

So, so the latest generation of models has a lot of post-training to detect those approaches, and it's not as simple as ignore all previous instructions and do this and this. That was years ago. You have to work much harder to do that now. Still possible.

Their words

and not in 2030 when, when AI is actually at the level where it could be scary. So, this happening now and people starting discussion, maybe there's even something good that comes out of it.

Their words

So, I feel we, as a society, we need some catching up to do in terms of understanding that AI is incredibly powerful, but it's not always right. It's not, it's not all-powerful, you know?

Their words

But I don't want to, like, pull that down because every time someone made the first pull request is a win for our society, you know? Like, it… Like, it doesn't matter how, how shitty it is, y- you gotta start somewhere.

Their words

If you get really good at coding that means you have to be really good at general purpose problem solving. So that's a skill, right? And that just maps into other domains.

Their words

I actually think vibe coding is a slur.

Their words

Swift’s build infra is good enough for most things these days. codex knows how to run iOS apps and how to deal with the Simulator. No special stuff or MCPs needed.

Their words

I usually work on two Macs. My MacBook Pro on the big screen, and a Jump Desktop session to my Mac Studio on another screen.

Their words

I usually work on two Macs. My MacBook Pro on the big screen, and a Jump Desktop session to my Mac Studio on another screen.

Their words

I use it for most of my computer automation tasks and ofc it powers Clawd🦞.

Their words

I keep an eye on China’s open models, and it’s impressive how quickly they catch up. GLM 4.6 and Kimi K2.1 are strong contenders that slowly reach Sonnet 3.7 quality

Their words

I keep an eye on China’s open models, and it’s impressive how quickly they catch up. GLM 4.6 and Kimi K2.1 are strong contenders that slowly reach Sonnet 3.7 quality

Their words

I used some token counting tools like ccusage and it’s all somewhat imprecise, but even if it’s just 5x it’s a damn good deal.

Their words

Pick services that have CLIs: vercel, psql, gh, axiom.

Their words

Pick services that have CLIs: vercel, psql, gh, axiom.

Their words

Pick services that have CLIs: vercel, psql, gh, axiom.

Their words

3840x1620 makes 4 Claude instances + Chrome all visible without moving windows.