miniblog.

I find that I'm choosing AI tools based on the quality of the harness rather than the model. For example, I'm using Claude Code Web because its model of remote VMs is extremely convenient. I'm using Perplexity because it's tuned really well for web searches.

I've realised that AGENTS.md / CLAUDE.md solve two distinct problems: * It tells the LLM the conventions of the project, avoiding follow-up prompts. * It precomputes a summary of the project, saving a bunch of searches at the start of a session.

Which programming languages are the easiest/hardest to google? Go (a common word) and Rust (also a computer game) can both be tricky. Yet I've not seen 'rubylang' used to help Ruby searches. Perhaps a novel word (Kotlin) or a misspelling (Perl) is a better choice for new languages?