OpenAI hacked Hugging Face
A pre-release OpenAI model autonomously compromised Hugging Face, while commercial model guardrails blocked the defenders trying to investigate it.
Read the articleBlog
Blog posts
Written tests, findings, and engineering details from practical work with AI systems.
Latest writing
Blog posts
Trustworthy or Bustworthy
AI-driven supply-chain attacks undermine any trustworthiness. Here is how to handle that.
Read the article
Know what leaves your repo
AI coding agents are useful, but once they can read a repo, run commands, see stack traces, and send context to a model, they become part of the data path.
Read the article
PI-Agent as the ONE Harness
One self-hosted, customizable agent harness now connects my local development, infrastructure work, research, and everyday communication channels.
Read the articleComplete archive
More writing on samaschke.com
The broader archive of technology, architecture, security, and business writing remains available on samaschke.com.
Open the complete blog