Comment by seanmcdirmid
11 hours ago
Most AI front ends seem to be designed for interactive jobs, so they make it hard to define a job that should be done eventually with zero priority. It makes much more sense to do that with spec-driven development (have work done with the human on the loop rather in the loop), but as far as I know that just isn’t well supported by any front end yet (would be happy to be proven wrong, my experience is with Google front ends).
There’s a lot of places where an llm can improve a data pipeline. Like if Claude sonnet was free I’d do a lot of data enrichment.