News for hackers. Stuff that matters.
Re:Auto-compact not triggering on Claude.ai despite being ma... by kachapopopow on Friday January 23, 2026 @03:33PM (#46737498)
They're A/B testing on the latest opus model, sometimes it's good sometimes it's worse than sonnet annoying as hell. I think they trigger it when you have excessive usage or high context use.
Re:Auto-compact not triggering on Claude.ai despite being ma... by hirako2000 on Friday January 23, 2026 @05:17PM (#46738728)
Or maybe when usage is low so that we try again.

Or maybe when usage is high they tweak a setting that use cache when it shouldn't.

For all we know they do whatever experiment the want, to demonstrate theoretical better margin, to analyse user patterns when a performance drop occur.

Given what is done in other industries which don't face an existential issue, it wouldn't surprise me some whistle blowers in a few years tell us what's been going on.