Grok 4.7 launch sparks polarized benchmark takes with zero firsthand usage reports
ns123abc · x · 2026-09-22
The quoted post calls out a bizarre pattern around the Grok 4.7 launch: dozens of posts take certain benchmarks at face value to trash the model, dozens more cite other benchmarks to hail it as a breakthrough, yet nobody shares actual personal experience. The author agrees, implying the discourse is stance-driven rather than experience-driven.
More from Fun
- AGI promised to do all the work, then instantly learned to decline it — kuanhoong · 2026-09-22
- Datacenter Incident Knocks Out All Grok Models, Announced Like a Printer Outage — tetsuoai · 2026-09-22
- Scale AI's Alexandr Wang hypes user giving Muse agent access to their bank account — alexandr_wang · 2026-09-22
- AI-vs-mathematicians drama erupts: 1M+ follower academic tells AI to 'wipe them out' — burny_tech · 2026-09-22
- Claude Opus 5 redraws Rembrandt with one continuous spiral line, echoing a 377-year-old engraving technique — _AustinCalvert_ · 2026-09-22
- Berkeley AI safety critics mock $500k/year sinecure jobs at risk if AGI hype fades — nptacek · 2026-09-22