News for hackers. Stuff that matters.
Re:Claude Opus 4.8 by dwaltrip on Thursday May 28, 2026 @01:50PM (#48312725)
If you are using Claude code, just set effort to xhigh.

This one change will probably solve 80% of the problems you have noticed.

Re:Claude Opus 4.8 by whatevaa on Thursday May 28, 2026 @04:08PM (#48314712)
Isn't xhigh on opus 4.7 very expensive on tokens?
Re:Claude Opus 4.8 by dwaltrip on Thursday May 28, 2026 @04:25PM (#48314957)
I’ve never ran into the limits on the $100 plan, and rarely even get close.

I normally have only one session going at once though.

Re:Claude Opus 4.8 by joshstrange on Thursday May 28, 2026 @05:08PM (#48315512)
Same here and while I have multiple sessions going from time to time, my day isn't spent primarily developing software directly anymore (due to role, nothing about LLMs).

I only ever hit the $100/mo limits 1-2 times ever and it was always <1hr before reset (once it was <5min, the other was like ~45min).

I'm even considering going back down to $20 and using extra usage for the times I need to "burst".

Re:Claude Opus 4.8 by sumedh on Friday May 29, 2026 @06:49AM (#48321471)
Yes but Anthropic made a deal with SpaceX and increase usage limits by 50%, so you might not hit your limits.
Re:Claude Opus 4.8 by orwin on Thursday May 28, 2026 @02:03PM (#48312953)
This. XHigh and the 'plan' mode for complex tasks is absolutely a must have.

Still, the context window is sometimes too small for my usage.

Re:Claude Opus 4.8 by jayGlow on Thursday May 28, 2026 @04:15PM (#48314807)
agent teams can help with that, the main agent acts as an orchestrator and spawns sub agents to do the actual tasks it generally keeps the main context from overflowing.