7 min
0
The Benchmark Paradox: Why We Broke Our Own Models to Find the Truth
In our last iteration of the OpenClaw lab, we built a hybrid routing engine. The…
OpenClaw Hybrid Routing: The Hallucination Sandbox and the Reality of VRAM
Have you thought about dumping a 32-billion parameter model into a 24GB GPU and magically…
9 min
0
The Agent’s Blindfold: Architecting a Zero-Trust Sandbox for Local AI
This blog post discusses the challenges and solutions in creating a secure environment for autonomous…
OpenClaw Benchmarks: Engineering Past the VRAM Iron Curtain
Outocomes are not the same thing as progress… The industry is currently obsessed with “vibe…
8 min
0
The Backup That Refused to Be Scheduled: A Lesson in “Parameters” Over “Vibes”
We tried to run a backup every day at 3 a.m. That’s it. That’s the…
7 min
0
Sharing my Coding Pipeline for AI assisted Software Development (v1)
In my recent posts, I’ve argued that Velocity is an Illusion and that to survive…
6 min
0
The Illusion of Velocity: AI, Premature Instrumentation, and the Death of Design?
Generative AI didn’t kill design. It made skipping design feel productive. When implementation comes first,…
3 min
0
Forcing IE compatibility in Edge with Enterprise Compatibility Mode
Our current web experience is filled with a myriad of web technologies, some refusing to…
10 min
0
A proposal for RCA in agile software projects
This publication was originally posted in spanish on November 4th, 2022 I am thrilled to…
8 min
0
A proposal for categorization of functional software defects
This post was originally published in spanish on march 21st 2021. In today’s dynamics, and…