Georg Unterholzner @georg_dev

Building @kipppunkt_dev. Softare engineer @Dynatrace. Data scientist turned software engineer. georg.dev Wien, Österreich Joined August 2013

Tweets

559
Followers

304
Following

270
Likes

3K

Georg Unterholzner @georg_dev

2 months ago

What's stopping you from coding like this?

0 0 1 22 0

View Details

@mattpocockuk I built a different agent orchestrator that puts more emphasis on the AFK part, and lets you essentially ship from your phone. It works with whatever sandbox you like and every AI harness. Check it out: kipppunkt.dev

0 0 1 43 0

View Details

Georg Unterholzner @georg_dev

2 months ago

Remember: a guy just spent 1100$ to have Codex reverse engineer Claude Code. I guess these tokens aged like fine milk.

Marcin Krzyzanowski @krzyzanowskim

2 months ago

I reimplemented "claude" CLI with codex and gpt-5.4-high. It cost $1100 in tokens, and is 73% faster and 80% lower resident memory during sustained interactive use. It is very easy to reverse claude from npm distribution, then reimplement is 1:1. It is indistinguishable from the

158 105 2K 1.0M 2K

0 0 1 72 0

View Details

Georg Unterholzner @georg_dev

2 months ago

I disagree with the last section. A dev building in tandem with an agent realtime will always be faster than writing extensive specs first, going AFK, and then fixing the slop. For solo founders / indie devs, AFK agents are great (can confirm - I'm building an AFK-agent AFK myself), but I haven't found any significant benefit in a setup where you're at your desk anyway.

0 0 0 84 0

View Details

Georg Unterholzner @georg_dev

2 months ago

@mitsuhiko This isn't the Vienna I know. Fixed it:

0 0 8 369 0

View Details

Georg Unterholzner @georg_dev

2 months ago

Sorry to break it to some of you but every AI engineering approach that requires you to write exhaustive specs beforehand is going to fail. Your specs suck. Always have. Always will. We learned that lesson decades ago.

0 0 1 36 0

View Details

Georg Unterholzner @georg_dev

2 months ago

@mattpocockuk I wrote a how-to about Docker devcontainer on Linux: georg.dev/blog/07-sandbo… But this doesn't support restricting network traffic and, therefore, allows data exfiltration. My learning was that I would need to switch to Podman and use OCI hooks for iptables config for that.

0 0 0 88 0

View Details

Georg Unterholzner @georg_dev

2 months ago

Sure! Rootless Docker means you run the Docker process (daemon) as normal user without special privileges. This means, even if a program inside the container would go rogue and manage to escape the container, it could only do limited damage on the host system. I'm not sure if that's actually a concern though, if you're on MacOS or Windows since there Docker uses a Linux VM, IIRC.

2 0 1 134 1

View Details

Georg Unterholzner @georg_dev

2 months ago

@mattpocockuk But then it's not rootless Docker, I suppose?

1 0 0 118 0

View Details

Georg Unterholzner @georg_dev

3 months ago

omg..

Zack Korman @ZackKorman

3 months ago

You can hide these !commands in html comments so people don't see them when reading the skill. The command executes without the AI even knowing about it.

32 71 885 122K 489

0 0 2 50 0

View Details

Georg Unterholzner @georg_dev

3 months ago

@AdamRackis I'd like to introduce you to my former self.

0 0 0 1K 0

View Details

David Cramer @zeeg

3 months ago

Why is it everyone with an absurdly futuristic AI take is someone who - as best I can tell - doesn’t work on (and often never has) real software that has real users and real requirements? More so, why do you trust them?

117 45 988 51K 67

View Details

Georg Unterholzner @georg_dev

3 months ago

@ryancarson As someone who's building something like this: agree, however, kanban is great for humans but awkward for agent management. Orchestrator state is prbly going to be the single source of truth in the long run. Until then, we'll most likely sync state back and forth.

0 0 1 263 0

View Details

Ryan Carson @ryancarson

3 months ago

100% of dev is going to be done in sandboxes in the cloud, controlled by kanban boards. Trust me, I love my local machine and gorgeous mac apps, but all of it is just a terrible form factor for running a team of agents effectively.

132 37 656 208K 316

View Details

Georg Unterholzner @georg_dev

3 months ago

AI this. Agents that. My tendency to build things 10x as complicated as they need to be is still the same.

0 0 1 28 0

View Details

Georg Unterholzner @georg_dev

3 months ago

@mattpocockuk Hi Matt, regarding sandboxing, why a Docker devcontainer and not just the built-in sandbox from Claude Code?

2 0 4 6K 1

View Details

Georg Unterholzner @georg_dev

3 months ago

If you use kipppunkt dev, you can: - do all of this out of the box - have the agent also ask clarifying questions on new GitHub issues - have all past decisions documented on GitHub - do everything in one UI you're already used to - do it afk from your phone

Matt Pocock @mattpocockuk

3 months ago

For weeks, folks have been asking me to make a video building a feature with Claude Code in a real codebase So here you go: - From idea to AFK agent to QA - Every single step explained - No slop allowed

60 106 2K 360K 4K

0 0 1 78 0

View Details

Georg Unterholzner @georg_dev

3 months ago

@ZackKorman skills sh is probably one of the most negligent things that have been released recently. The CLI even tries to convince you to install a skill to sideload random skills smh Still can't believe we settled on this being the way doing things just because "Vercel"

1 1 17 1K 0

View Details

Georg Unterholzner @georg_dev

3 months ago

@fjzeit For anyone interested, I built such an agent orchestrator. That's also why I'm convinced that it works, because I have it working on my machine: kipppunkt.dev

0 1 1 37 0

View Details

Georg Unterholzner @georg_dev

3 months ago

@fjzeit Going back to waterfall was always a bad idea. I still believe, you can have an automated loop, though. But it needs to have small iterations and the dev needs to be briefly involved on every iteration.