| Github | https://github.com/sttts |
| https://twitter.com/the_sttts |
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
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.
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.
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
Alt, aber immer wieder beeindruckend zu sehen: Arithmetik mit Wörtern. Hier mit unserem GPT-2-Class-Modell und Tokenizer (Credits gehen an @surbaniak, der hat den trainiert) Nanoschnack https://github.com/nanoschnack/nanoschnack/ trainiert nur mit deutschen Texten.
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: https://community.cncf.io/events/details/cncf-cloud-native-heidelberg-presents-building-a-gpt-2-model-from-scratch-nanoschnack/cohost-cloud-native-heidelberg/
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
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.
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.
#transformers #attention #tokens #embeddings #training #pytorch #h100 #inference
It’s enterprise when you port the Claude https://github.com/steveyegge/beads workflow to native Jira. And it works using https://github.com/ankitpokhrel/jira-cli 🎉
I have never commented so much in Jira issues about progress. Well I still don’t but now Claude does for me. Try it.
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.
