logoalt Hacker News

gordonhartyesterday at 9:05 PM3 repliesview on HN

Honestly curious, have you seen agents succeed at this sort of long-trajectory wide breadth task, or is it theoretical? Because I haven't seen them come close (and not for lack of trying)


Replies

codegangstayesterday at 9:42 PM

Yeah I absolutely see it every day. I think it’s useful to separate the research/planning phase from the building/validadation/review phase.

Ticket trackers are perfect for this. Just start with asking AI to take this unclear, ambiguous ticket and come up with a real plan for how to accomplish it. Review the plan, update your ticket system with the plan, have coworkers review it if you want.

Then when ready, kick off a session for that first phase, first PR, or the whole thing if you want.

kolinkoyesterday at 10:59 PM

In my expedience, Claude Code with opus 4.5 is the first one to tackle such issues well.

fragmedeyesterday at 11:25 PM

Opus 4.6, with all of the random tweaks I've picked up off of here, and twitter, is in the middle of rewriting my golang cli program for programmers into a swiftui Mac app that people can use, and it's totally managing to do it. Claude swarm mode with beads is OP.