I wrote a blog post for the project this week detailing some of the challenges the QEMU project, in common with other FLOSS projects, are seeing with AI generated bug reports. The dilemma being that the LLM's have got to the point they generate better bug reports than a lot of humans do.

Watching #emacsconf today I was introduced to this open source project to act as an agent between #llm's and editors.

Has anyone played with this? Any experience in how one would sandbox an agent so it doesn't do anything outside the project directory?

This is depressing. I have relatives who are adopters and it seems this sort of behaviour of social workers is endemic in the system. The support is not there and when things break down they attack the parents to bully them into continuing at risk to themselves and their other kids.

A fairly deep dive about how you can cherry pick stats to push a narrative.