One interesting consequence of the rise of LLMs: there's more demand for tools that handle untrusted input.
Arbitrary HTML+JS can be safely run in a browser. Lean can check an arbitrary proof.
These work really well with an LLM that can be wrong, but sometimes gives exactly what you want. Are there other tools in this family?
Related Posts
... and my third refactoring with Cursor changed some function calls that I didn't want it to modify. Subtle.
I've had the most success with AI coding tools when I know exactly what I want the output to look like.
LLMs seem to handle dependency upgrades really well.
The task is well-specified, there's usually a build/test suite to check correctness of the modifications, and there's often a changelog they can consume too.
Today I learnt that you can mix HTML inline in markdown! For example, the following is valid.
Foo <hr/>
I'd assumed that you needed HTML separately, like ``` blocks, but no: https://spec.commonmark.org/0.31.2/#raw-html
Admittedly HTML is very restricted on most sites, but it's helpful for SSGs.