As a possible example of this, I was kind of baffled how quickly we're all now throwing the sophisticated AST/program analysis and refactoring methods over board we already had before AI. Just look at the refactoring methods of Eclipse or IntelliJ.

I think those should be very useful, especially with AI: Either as a tool for the agents themselves - why spend heaps of tokens completely rewriting a code file, if you could do most of it by calling some global refactoring operations on the IDE's AST/symbol database?

Or side-by-side with it, to give human users better insight what the AI did.

Instead it seems to be all VSCode (if at all) + grep + AI agents, and nothing else.

This is an interesting idea! I searched around and it looks like there's [ast-grep](https://ast-grep.github.io/), an AST-aware CLI that can search and refactor code -- and you can expose it to your AI agent using a skill (https://github.com/ast-grep/agent-skill).

Not exactly symbolic AI, but pretty cool nonetheless.

> especially with AI

Yeah, the middle path sounds promising.

"Code Mode", where the AI writes a little program or script to do the AST/symbol transformations sounds like the win. As you point out, less tokens, and gives the humans insight.

This isn't exactly the same application of a "code mode" as before, but in my view it's a broad philosophy. AI for building machines, instead of doing the work directly. It also allows for easier updates/retries too. https://blog.cloudflare.com/code-mode/ https://news.ycombinator.com/item?id=45399204 https://blog.cloudflare.com/code-mode-mcp/ https://news.ycombinator.com/item?id=47089505