> any time our instinct says "don't build that, it's not worth the time" fire off a prompt anyway
I disagree with this sentiment. This approach leads down to huge maintenance burden.
I disagree with this sentiment. This approach leads down to huge maintenance burden.
> For now I think the best we can do is to second guess ourselves: any time our instinct says "don't build that, it's not worth the time" fire off a prompt anyway, in an asynchronous agent session where the worst that can happen is you check ten minutes later and find that it wasn't worth the tokens.
This shouldn't lead to huge maintenance burden because most of the time you'll throw away the result. It's a learning exercise.
That coding got cheaper shouldn't change prioritization post planning. It should definitely factor into prioritization at planning time.