Miles Brundage: Opus 5.5 Max 'works fairly hard', first time he skips defaulting to Ultracode
Miles_Brundage · x · 2026-09-24
Former OpenAI safety VP Miles Brundage shares first-hand impressions: Opus 5.5 Max works fairly hard on tasks, marking the first time he no longer defaults to Ultracode for all non-trivial work — a sign the two are now close in real-world performance.
Related event: Developers Praise Anthropic's Opus 5.5 After Hands-On Tests(11 posts)→
More from Models
- Developer slams Claude quality drop: simple debug now burns 70 tool calls — Muritavo · 2026-09-24
- Hands-on: Claude Opus 5.5 beats GPT-6 Sol and Luna on creative briefs — MattVidPro · 2026-09-24
- Independent eval of Opus 5.5 vs GPT-6 across 100 coding environments diverges from AAII — sandersted · 2026-09-24
- OpenAI's Neon Connector Reaches Voice Mode but Project-Level Actions Fail on Missing project_id — koltregaskes · 2026-09-24
- Astra and Grok 4.7 sit at opposite ends of accuracy and token-usage charts in CAIS eval — polynoamial · 2026-09-24
- Report: 'GPT-6 Luna (max)' scores 18.3 at n=3, degradation allegedly confirmed — unverified — PawelHuryn · 2026-09-24