miniblog.

Playing with Hermes Agent and it's the first agentic tool where I feel I need to *justify* my changes. It's updating its notes over time. W: Split those two jobs, they're completely unrelated. H: Done. I also updated the skill to note that unrelated topics should be split.

LLVM's lit tool for testing files is the most successful testing DSL I've ever seen. It's used a decent number of projects outside of LLVM. By contrast I don't see many folks using e.g. Cucumber these days.

LLMs are surprisingly good at reducing crash samples. I've had success with "this project crashes my static analysis tool with the following command, try to shrink the repro whilst preserving the crash. Commit each smaller version to a branch".