I just posted to my Substack a quick guide to run Stable Diffusion locally. It covers the basics, from setup to inpainting to correct errors. [Read More]

This week was released a report about the declining code quality since the introduction of AI (it can be found here). GitHub advertises Copilot with numbers like +55% faster coding, +46% code written, +75% more fulfilled, 20.000 organisations using that tool, and 92% of US-based developers in large companies using AI. [Read More]

All people working in software development experience friction when they try to promote innovation. With innovation, I do not mean introducing fancy AI or blockchain in a web service, but any action that moves the status quo by more than an inch. Even changing a library is problematic sometimes! [Read More]

Brief experiment to compare medical models and run them locally. [Read More]

Running LLMs locally on commodity hardware may be challenging. The setup is definitely not trivial, the requirements are very high, and the end result is typically disappointing due to bad performance. [Read More]