Robdel12

I wanted a real native app (iOS/macOS) as a client for my agents and to be able to truly control / mange them from it. So, think Claude Code remote but not just Claude and a proper native app. Or the Codex app but actually native.

The server is a rust binary so you can toss it on any container/computer and connect to it in the app.

My philosophy isn't to replace my other tools I love like emacs, ghostty, etc. But I am taking a stab at "real time code review" and have some crummy magit-like code review built in that I need to revisit.

https://github.com/Robdel12/OrbitDock

So will there be droves of people canceling their Claude subscription too?

None of these companies are clean and I think it’s hilarious HN and the rest of SV has been duped by Dario. He’s playing the game better than Sam is, imo. Nothing Dario has said has indicated he is regretful about their partnership with Palantir or any of the stuff they’ve done with the DoD in the past 2.5 years.

Edit: this Washington Post article seems to be the original source: https://www.washingtonpost.com/technology/2026/03/04/anthrop...

Ha, I’ve had a Mattermost instance for years until they handicapped the most recent version by limiting the number of messages on the self hosted version.

I ended up building my own alternative and was going to OSS it but like… there’s already a bunch out there.

Anyway, Mattermost might not be the choice these days. With that stunt I was annoyed enough to spend a weekend to replace what they were to me.

This is only the beginning. People are far far too reckless with their LLMs.

I am still heavily checking everything they’re doing. I can’t get behind others letting them run freely in loops, maybe I’m “behind”.

Heyo! I figured I’d share something I’ve been thinking about over the past month or so. I’m curious if anyone else is feeling/thinking this?

Everything is moving so fast, my head is spinning.

That’s AGI, right? For the model to learn novel things itself and retain it?

I have no idea but I’m along for the ride!

I retired my M1 MacBook Air last year, really out of power greed. I wanted to play with local LLMs (lol).

I seriously never had issues with my m1 in my workloads. Dev stuff, docker, etc. editing 30min 4k GoPro videos. I probably would these days with rust dev stacked in there but yeah. Can’t agree more, they’re an amazing value.

Hey!… no yeah you’re right.

Hey, they did admit that they vibed this in a week and released it to everyone.

YES, I have been thinking the same and wrote a bit about it: https://vizzly.dev/blog/cli-json-output-llm-friendly/

Thank you so much to the GH CLI for making me realize this, really. The only MCPs I use still are ones that don’t have CLIs. Hell, I even just wrote a CLI for Bear Notes, for LLMs. It’s just better.

Seems like the last MCP use case is model to model communication but I’m sure others have approach’s for that?

I’ve gotten the absolute best results from LLMs just acting like the software engineer I’ve aspired to be the past 15 years.

Normal dev things. Scope the ticket properly, break it down. Test well. Write the correct docs.

LLM specific things are going to be gone next week

Whether we want to accept it or not, we’re now QA. That’s not derogatory, at all.

But I don’t think the answer here is to double down on reading the code and understanding that deeply. We’re rapidly moving past this.

I think the answer is to review the code for very obvious bad choices. But then it’s about proper validation. Check out the app, run the flows, use it for real. Does it _actually_ function?

Or that’s what is working for me. I cannot review all the LOC and I’m starting to feel like I don’t want.

Yeah, you’re right. I’m overly hopeful and naïve

Edit: as soon as I hit submit I realized this might sound condescending, but I actually mean this lol

I guess I’m hanging on what

> reflects them in law

Means exactly. What law and what does it say?

I’m also sure he quietly bent the knee, but I want to know what “law and policy” it’s being reflected in to know.

Raise your hand if you actually read it or if you read the title and replied? I see a lot of comments that sure seem like they didn’t read it.

> Two of our most important safety principles are prohibitions on domestic mass surveillance and human responsibility for the use of force, including for autonomous weapon systems. The DoW agrees with these principles, reflects them in law and policy, and we put them into our agreement.

IF this is true, it SHOULD be verifiable. So, we wait? I mean, I am a dummy, but that language doesn’t seem too washy too me? Either it’s a bold face lie and OpenAI burns because of it or it’s true and the Trump admin is going after the “left” AI company. Or whatever. My point is, someone smarter than me/us is going to fact check Sam’s claim.

And we can't forget the nationalism at the time. Everyone was rallied behind the program and wanting to beat the Soviet Union. I mean, sputnik scared the hell out of everyone.

I think that's probably important framing for how things were reported back then. But also, I'm wrong like 99.9999999% of the time. So!

They're getting slightly bullied into following their own rocket certification process. Wild they're going right to human flight without their three unmanned certification flights, etc. NASA themselves will not allow mission critical payloads on rockets that don't meet that process. But they're (trying) to skip it with Artemis.

I really appreciate the gesture, but this kind of feels like it’s an attempt to claw (lol) some good will back from devs. The barrier is way too high, imo. And the 6 month cap does make sense given the cost of LLMs but it’s a bad feeling. We like you, but for 6 months.

As a tinnnyy plug, I’ve ran OSS sponsorship programs before for companies. One thing that I always hated was the sales contact process to get it. So, for Vizzly I made it 100% automated. Sign up, connect an OSS public repo, get a free plan. https://vizzly.dev/open-source/ I don’t wanna talk to you and you don’t wanna talk to me (for this :p)

Honestly, build it yourself. I think we’re firmly in the personal software era (or disposable).

But if you don’t want to, I’ve been building basically this https://github.com/Robdel12/OrbitDock

Native macOS and iOS apps, backed by a rust binary that I put anywhere and connect to. Right now I’m just LAN but eventually will tailscale.

Works with claude and codex. Both passively watching an active CLI session for both and you can take over those sessions if needed and interact in the app

This is buggy to no end. Anthropic needs to slow down

The daily “what broke and changed now” with claude code is wearing me out fast.

Heh, I felt the same. I'm a web dev but I do not want a electron app. We can do better, I used to write electron apps because I wasn't able to build a proper native app. Now I can!

I've been building a native macOS/iOS app that lets me manage my agents. Both the ability to actually control/chat fully from the app and to just monitor your existing CLI sessions (and/or take 'em over in the app).

Terrible little demo as I work on it right now w/claude: https://i.imgur.com/ght1g3t.mp4

iOS app w/codex: https://i.imgur.com/YNhlu4q.mp4

Also has a rust server that backs it so I can throw it anywhere (container, pi, etc) and the connect to it. If anyone wants to see it, but I have seen like 4 other people at least doing something similar: https://github.com/Robdel12/OrbitDock

This is actually an excellent idea, I’ll give this a shot tonight!

I really want to use google’s models but they have the classic Google product problem that we all like to complain about.

I am legit scared to login and use Gemini CLI because the last time I thought I was using my “free” account allowance via Google workspace. Ended up spending $10 before realizing it was API billing and the UI was so hard to figure out I gave up. I’m sure I can spend 20-40 more mins to sort this out, but ugh, I don’t want to.

With alllll that said.. is Gemini 3.1 more agentic now? That’s usually where it failed. Very smart and capable models, but hard to apply them? Just me?

> according to Bloomberg's Mark Gurman.

The entire Apple rumor world is based off this guys Sunday email.

I’m a heavy Claude code user and it’s pretty clear they’re starting to bend under their vibe coding. Each Claude code update breaks a ton of stuff, has perf issues, etc.

And then this. They want to own your dev workflow and for some reason believe Claude code is special enough to be closed source. The react TUI is kinda a nightmare to deal with I bet.

I will say, very happy with the improvements made to Codex 5.3. I’ve been spending A LOT more time with codex and the entire agent toolchain is OSS.

Not sure what anthropic’s plan is, but I haven’t been a fan of their moves in the past month and a half.

Salesforce is the worst, lol

I really really want local or self hosted models to work. But my experience is they’re not really even close to the closed paid models.

Does anyone any experience with these and is this release actually workable in practice?

The effort put into it is not “just a joke”. The creator knows exactly what he did and the joke excuse is weak

This is realllly cool. I have a rabbit hole to go down into tonight

I’ve always enjoyed creating working things for people to use. Which is why I love LLM coding agents.

Is it wild the thing I took a while to learn is now done basically by a GPU? Yes. But hand writing code is not my identity. Never has been.