User: Astra Has 'Hemorrhaged IQ' in Codex, Opus 5.5 Is King Again
sterlingcrispin · x · 2026-09-26
Artist Sterling Crispin reports a reversal in model quality: a week after ditching Claude for feeling dumber, he finds Astra inside Codex has 'hemorrhaged IQ' — responses feel like Abbott and Costello's 'Who's on first?' skit — making Claude Opus 5.5 his top pick again. He wonders what's going on at OpenAI. The post captures how frequently updated frontier models swing in quality week to week.
Related event: Developers Say Astra's Performance in Codex Dropped Sharply Within a Week(2 posts)→
More from Models
- Micius-Flash: 27B Multimodal Model for Hardware and Semiconductor Agents — zhiman-ai · 2026-11-11
- Baidu says RSI auto-optimized ERNIE inference, 6.24x decode speedup on Kunxin P800 — xiaohu · 2026-11-11
- Baidu's ECHO: multi-token prediction reusing the last layer as a drafter — xiaohu · 2026-11-11
- ERNIE 5.5 Flash Preview: 280B-param multi-router MoE activating only 14B per token — xiaohu · 2026-11-11
- ERNIE 5.5 recreates the Pelican test: 117-second animation drawn frame-by-frame in Python — xiaohu · 2026-11-11
- 35,000+ Grok-built apps exposed patient data, plaintext passwords, and sales pipeline — The Decoder · 2026-11-11