@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: https://t.co/Paa5aZeBoh
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 Anthropic version to the every header and analytics it send back
https://t.co/2tpEB4SPIb
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.
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.
@mattpocockuk I wrote a how-to about Docker devcontainer on Linux: https://t.co/9MHJSVf1Dx
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.
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.
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.
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?
@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.
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.
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
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
@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"
@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: https://t.co/Paa5aZeBoh
@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.