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 think you could build an interesting IDE with a tiny embedded LLM in addition to the usual tooling.
Features like 'extract method' would be much nicer if an LLM could provide a name. Choosing a good name is virtually impossible from just a typed AST.
Blogging about my programming language project: choosing the basic syntax!
