x-feeds — the daily AI metaOne pick per day: what AI Twitter was actually talking about.https://x-feeds.pages.dev/Claude Opus 4.6 plummets on BridgeBench after retest — hallucination rate nearly doubles and lab rivalry igniteshttps://x-feeds.pages.dev/2026-04-13/https://x-feeds.pages.dev/2026-04-13/CLAUDE OPUS 4.6 IS NERFED. BridgeBench just proved it. Last week Claude Opus 4.6 ranked #2 on the Hallucination benchmark with an accuracy of 83.3%. Today Claude Opus 4.6 was retested and it fell to #10 on the leaderboard with an accuracy of only 68.3%. A 98% increase in hallucination. — @bridgemindaiMon, 13 Apr 2026 00:00:00 GMT