Stop Using Your LLM as a Scheduler
I run a multi-agent coding system on a single AMD Strix Halo box: 128 GB of unified memory, one iGPU, four agent roles …
Read morePosts
LLMs: Legal Implications? Some things to consider
Everyone and his dog these days seem to use large language models (LLMs) like ChatGPT, Claude, Gemini or Copilot. From …
Read moreTerraform Training - Getting Started with Terraform
Get your team up and running with Infrastructure as Code. Our hands-on Terraform training takes participants from first …
Read moreRecruiting Without Assignments
A coworker once joked: “They made me design a reversed binary tree during the interview, but all I do day-to-day …
Read moreExit Plan: A much needed addition to your Business Continuity Plan
Current state of the market
Time for radical change, the momentum is there, the need was already there, but finally the …
Read moreLocal LLMs in Open-WebUI with MCP server
MCP Servers are currently the new hipster thing to do in the LLM landscape, and for good reason. No longer do you have …
Read moreHow to prevent burnout as a Techlead
Being a Techlead sounds like a dream job: You get to decide everything, you will get no pushback and everyone will …
Read moreNavigating etcd v3 waters
A post about etcd v3, mainly about how paths work in v3.
Today I was playing around with an empty etcd v3 cluster, …
Read moreKeybase broken on the M1 Pro
Recently I needed to get access to Keybase since I bought the M1 Pro. During the first try to sync the folders in a …
Read more