[meltyness]

I'm more interested in how users are taking 95-99% to 99.99% for generation-assisted tasks. I haven't seen a review or study of techniques, even though on the ground it's pretty trivial to think of some candidates.

[oezi]

Three strategies seem to be:

- Use LLM to evaluate result and retry if it doesn't match.

- let users trigger a retry

- let users edit