News for hackers. Stuff that matters.
Re:Claude Opus 4.8 by ThunderBee on Thursday May 28, 2026 @04:45PM (#48315207)
IME the most noticeable performance boosts are in complex multi-agent workflows.

EX. You call an orchestration agent and define an implementation plan with the help of a number of sub agents planning out different features. You and the lead agent review all of the plans and send them off to a set of agents that write tests which get send back to the orchestrator then passed along with the plan to a set of coding agents who implement the features in their own worktrees. That gets passed back to the orchestrator which hands it off to another set of agents doing the code review and merging the features before sending it back to you.

Re:Claude Opus 4.8 by 8note on Thursday May 28, 2026 @04:53PM (#48315301)
i dont think theres anything particularly special about new models for that though. thats a harness improvement
Re:Claude Opus 4.8 by adi_kurian on Thursday May 28, 2026 @10:00PM (#48318082)
1mm context window is pretty big. Even if dumber, opens new avenues. For the record I don't think we ever got better than 4 and 4.1.