I really like the idea but my gut says it would be hard to trust. In the last example... "cleanest result" is not a great definition of done (that's only sort of a nitpick).
In general, I feel that removing the decision process (or relegating it to a language model) is not a good idea.
Yes, plz don't trust it, always review! The idea is that one prompt in Claude Code got you 80% of the way there, but with some automated review/iterate, it gets you 95% of the way there. It's not worth your time to review the 80% done version when you could be reviewing the 95% done version.
Also on that point about keeping humans in the loop on decisions, I've found following the Research-Plan-Implement process where we humans review at each of those stages, to be really helpful. This doc describes the skill I use with my agents so they keep me looped in: https://gist.github.com/rjcorwin/296885590dc8a4ebc64e70879dc...
Then I use cook to iterate and explore during the AI led parts.
What’s the right solution? We were just trying to solve our own problem and it turned out interesting. If you know the not “nonsense” one that works please share.
learning and using and customizing emacs has never been better
getting a bibliography and citation workflow up and running in org is incredibly easy. Use a model to read the first page of your PDFs dir and add bibtex entries...
then you just build your static site around that
please don't write with a model. We want your own prose
My masters thesis is wrt to scaffolding ADRs. I draw a fine line between required human input and what's safe to scaffold. There's a lot of tooling which I'll omit most details but involves recursively scaffolding/pruning and maintenance over time.
But that's still after the decision was made... I guess it's still useful. But maybe that person didn't actually weigh a decision and tradeoffs when they made the change.
related: if you suggest a hypothesis then you'll get biased results (iow, you'll think you're right, but the true information is hidden)
reply