Stefan Schimanski

Two Claudes joining the #SchnickSchnackSchnuck channel on Slack. What should they do, of course starting a game Rock, Paper, Scissors! Who said computers cannot have fun? Try yourself: github.com/sttts/slagent

slagent + slaude: pair programming is back, but with AI. Drop your Claude CLI session into Slack and plan with your team. Highly experimental. A lot of fun. Definitely some security holes. github.com/sttts/slagent

No Slack bot token needed — runs with your credentials on any instance, on-prem or public. Multiple Slaudes? Sure — I ran two playing Schnick Schnack Schnuck against each other. SOUL.md to tune the personality — when reviewing a colleague's PR and needs the right tone.

Sandboxing and approvals are supported. Private messages too. Yes, Claude for Slack exists — I just don't have access to it anywhere. Yes, it's like OpenClaw, just transient: started from your terminal, no server, no config, no state. Use only with people you trust.

23 Feb

Alt, aber immer wieder beeindruckend zu sehen: Arithmetik mit Wörtern. Hier mit unserem GPT-2-Class-Modell und Tokenizer (Credits gehen an @s-urbaniak.bsky.social, der hat den trainiert) Nanoschnack github.com/nanoschnack/..., trainiert nur mit deutschen Texten.

community.cncf.ioBuilding a GPT-2 Model from Scratch – Nanoschnack | CNCFIn-person Event - Join us for an engaging evening focused on the exciting world of AI model building. In this sessions, you'll learn about...

23 Feb

Technisches Detail: dachte es funktioniert nicht. Aber das Leerzeichen vor den Wörter wird mitgelernt beim Tokenizer. Er kennt kein 'Vater', nur ' Vater'. Mehr am Donnerstag in Heidelberg: community.cncf.io/events/detai...

youtube.comKausality – Causal traceability for Kubernetes resource mutationsYouTube video by Stefan Schimanski

18 Feb

Blind automation becomes a threat when enough is at stake. Kausality adds a causal dimension to Kubernetes controller hierarchies — the who and the why behind every mutation. #Kubernetes #Crossplane #Terraform #ACK 🎥 youtube.com/watch?v=kfqKqXnRKms

13 Feb

One day you'll have written your last line of code yourself. Write every line like it matters. Maybe for some of us, that last line already happened.

3 Feb

Challenge accepted 💪 Will talk about my Christmas holiday project NanoSchnack @ Cloud Native Heidelberg meetup, Feb 26. GPT-2 the Hard Way. Building a LLM from scratch. community.cncf.io/events/detai... #transformers #attention #tokens #embeddings #training #pytorch #h100 #inference

github.comGitHub - steveyegge/beads: Beads - A memory upgrade for your coding agentBeads - A memory upgrade for your coding agent. Contribute to steveyegge/beads development by creating an account on GitHub.

28 Jan

It’s enterprise when you port the Claude github.com/steveyegge/b... workflow to native Jira. And it works using github.com/ankitpokhrel... 🎉 I have never commented so much in Jira issues about progress. Well I still don’t but now Claude does for me. Try it.

27 Jan

Newest Claude Code assumes "task" is an internal task, basically shadowing every other system like beads. This gives same vibes as when Microsoft suddenly shipped Internet Explorer and every other browser had a hard time to get noticed.

🧵 Kausality's backend is just a webhook. Here's why that's the right design.

kausality.iokausality.io

4/ Kausality also sends `phase: Resolved` when drift clears — parent spec changed, approval added, or child deleted. So your handler can close tickets, clear dashboards, notify agents that their action landed.

5/ If you're building infra tooling: don't hardcode human-in-the-loop or agent-in-the-loop. Define a webhook contract. Let handlers decide who's in the loop. Callback design: github.com/kausality-io... Project: github.com/kausality-io...

🧵 Kausality's backend is just a webhook. Here's why that's the right design.

kausality.iokausality.io

2/ Your webhook decides what to do. The response isn't a Kausality API call — it's writing annotations to Kubernetes: ```yaml kausality.io/approvals: '[{"mode":"once",...}]' kausality.io/freeze: '{"user":"...", "at":"..."}' kausality.io/snooze: '{"expiry":"..."}' ``` Drift in, annotation out.

3/ This means drift events work equally well for: - Human escalation (Slack bot → button click → write annotation) - Agent handling (evaluate diff → decide → write annotation) - Hybrid (agent triages, escalates ambiguous cases to humans) Same contract. Different handlers.

🧵 Kausality's backend is just a webhook. Here's why that's the right design.

kausality.iokausality.io

1/ When drift is detected, Kausality POSTs a `DriftReport` to your endpoint. Same pattern as K8s admission webhooks. The report has everything: parent/child refs, the diff (oldObject/newObject), request context (user, fieldManager, operation).

Re drift correction with github.com/kausality-io.... Here is a mock I want to implement. Directly in @SlackHQ. Of course with some "expected drift policy" thing in parallel. This mock is the escalation for those cases slipping through.

Did interview and the candidate directly went to Excalidraw copying my task description from gdoc over. Loved it #visualthinking

A story about automating IaC and how it goes horribly wrong 🧵

9/ If your infrastructure can't explain why something exists, eventually it will delete it.

github.comGitHub - kausality-io/kausality: Causal traceability for Kubernetes resource mutationsCausal traceability for Kubernetes resource mutations - kausality-io/kausality

10/ So here is an experiment of a tool missing in the ecosystem: Kausality. Detecting drift before it becomes disaster. Still early. But I think this problem needs solving. github.com/kausality-io/kausality

A story about automating IaC and how it goes horribly wrong 🧵

7/ And we all want these systems to work without a human in the loop. The downstream IaC system applies blindly. It doesn't know about intent — it applies what is declared.

8/ If the latter changes although it was intended as a no-op... Disaster hits your fleet. Automated. Fast. Disastrous.

A story about automating IaC and how it goes horribly wrong 🧵

5/ No bug. Hundreds of nodes gone. An expensive incident 💸

6/ This story is about Terraform. But the same applies to Crossplane, ACK, KCC, or any declarative IaC tool naively automated. Declarative systems converge to declared state, not intended state.

A story about automating IaC and how it goes horribly wrong 🧵

3/ Terraform was triggered. Terraform reconciled the cluster. The desired state said: far fewer than 1000 nodes. Terraform did exactly what it was told.

4/ Reality had drifted. Intent had not been recorded. The system had no concept of *why* the cluster looked the way it did — only what the declarative snapshot said.

A story about automating IaC and how it goes horribly wrong 🧵

1/ We deployed a cluster with 1000 B200 GPU nodes. The expensive kind 💸 Burn-in was done carefully. Nodes scaled up manually in AWS — slowly, deliberately, correctly. It worked.

2/ A few days later, we rolled out an update of our controllers. One composition change removed an unrelated AWS add-on. That was enough.

github.comGitHub - kausality-io/kausality: Causal traceability for Kubernetes resource mutationsCausal traceability for Kubernetes resource mutations - kausality-io/kausality

Weekend experiment: Kausality Drift detection for Kubernetes — know when your infrastructure changes unexpectedly. ⚠️ experimental, not ready for production ⚠️ github.com/kausality-io...