mirror of
https://github.com/Jeffrey-Sardina/liberated-systemd.git
synced 2026-10-19 01:29:53 -05:00
Daan De Meyer
a31540ec82
At high effort, Opus 5.5 uses about half as many thinking tokens per review as Opus 5 did. The lenses return after about five of their twenty minutes. Use xhigh effort, and tell the lenses to go through every hunk of the diff instead of stopping at the first findings.