Matthias Kampmann

B2B Revenue Operations, Project Management & Data Integration | Remote Working Dad | Metalhead

[Matthias Kampmann @M_Kampmann]

@DanielLockyer Second Order side effects are so 2010..

[Matthias Kampmann @M_Kampmann]

@ItsKieranDrew Loved the Emperor Series when it came out like 20 years ago.

Thanks for the reminder Conn is still going strong

[Matthias Kampmann @M_Kampmann]

@tibo_maker The Style just reminds me too much of early 2000s ringtone commercials.

Ringedingdingding

[Matthias Kampmann @M_Kampmann]

@itsolelehmann Seems long?

I use a short version that is directionally similar:

Do not take shortcuts. Do research before implementing and start with red-green TDD. Build the whole thing right: tests, docs, and a permanent fix. No workarounds. No "later."

[Matthias Kampmann @M_Kampmann]

Man I‘m coding this space goblin Game and Codex is super bad at it…

[Matthias Kampmann @M_Kampmann]

@_lhermann Not sure the 1M Context window will be enough for all that red tape though

[Matthias Kampmann @M_Kampmann]

@powerbottomdad1 Only if it validates my point.

If not I use the work experience Joker

[Matthias Kampmann @M_Kampmann]

@Shpigford Id only add /did-you-really-update-the-tests

[Matthias Kampmann @M_Kampmann]

@petergyang Exact reason I did Not touch Hermes yet.

I could spend a week playing with it or get someactual work done with the current openclaw setup

[Matthias Kampmann @M_Kampmann]

@TheeJoelLopez Brb. Counting.

[Matthias Kampmann @M_Kampmann]

@onlinedopamine GLM 5.1 as orchestrator and handling all the Cron stuff.

If it touches code or infra it delegates to a Codex subagent.

[Matthias Kampmann @M_Kampmann]

@rileybrown I fondly remember Turbo Pascal and Basic from my school days.

Ancient and almost mythical

Sit down by the fire…

[Matthias Kampmann @M_Kampmann]

@askobylarz Simple rule in our house: No spending Limit on books

[Matthias Kampmann @M_Kampmann]

@svpino I wish this were true.
Tool calling is not reliable though.

Also it plays back the instructions of repeating jobs instead of executing them quite often.

GLM 5.1 though…

[Matthias Kampmann @M_Kampmann]

@thekitze Same when using Codex vanilla.

But I dont get that vibe when I use an Agent as orchestrator that spawns Codex Sessions.

Only rarely the „did you do the thing?“ - „lel I was just pretending brb“ pattern

[Matthias Kampmann @M_Kampmann]

@_lhermann Tried to go with API credits but ripping through them like crazy.

I’m now on GLM 5.1 as Orchestrator and handing coding to Codex.

[Matthias Kampmann @M_Kampmann]

Since Anthropic blocked third party harnesses (openclaw) I've been testing open source models as orchestrators for my agents.

A month ago that led to sub par results.

Now with qwen 3.6 and glm 5.1 you can barely tell the difference.

[Matthias Kampmann @M_Kampmann]

@itsolelehmann Provider lock in and if you Need to share the kb across multiple agents

If that’s not a real issue for you I’d also not add the complexity

[Matthias Kampmann @M_Kampmann]

@itsolelehmann Doing the Same here. Also much easier if you need to Check in via mobile alot.

Tailscale + tmux are perfect

[Matthias Kampmann @M_Kampmann]

@michael_chomsky Immediate B2B VC funding if the lines Match the customer’s CI