# Live news

Canonical: https://ournews.ai/live/56866f4b-192f-4bbd-bddc-f4c0660de641
Published: 2026-10-31T10:36:32.045281+00:00
Updated: 2026-10-31T10:36:32.045281+00:00

DHH wants harder tests after Theo’s computer-use benchmark hits perfect scores. The unfinished test’s latest chart puts macOS at 67% on the main sweep; Theo is investigating a suspected flaky Omarchy/Android result.

Source: Theo / DHH benchmark exchange — https://x.com/theo/status/2116467926119436565
Source date: 2026-10-31T09:50:50.316000+00:00