Allie Miller: Claude leads on models, Codex on features — she uses both
alliekmiller · x · 2026-10-19
AI creator Allie Miller says Claude leads on model quality and behavior — Opus 5.5 is still her daily driver — but Codex wins on features and modalities. Live voice mode, computer use, and image generation are powerful enough that she'd rather accept a slightly worse model to get them.
More from Models
- GPT-6 Astra Pro adds parallel agents in ChatGPT, but users say deep thinking got worse — thomasahle · 2026-10-19
- Cloudflare ships Clef-omni: full multimodal decision model with ~130ms median latency — dl_weekly · 2026-10-19
- Models can easily detect probes and inference runtime changes, researcher finds — brandon_xyzw · 2026-10-19
- Qwen 3.8 27B tested locally on NTX Spark (Surface Laptop Ultra) — draginol · 2026-10-19
- GPT-6 answers increasingly include "how to select vendors" disclaimers, SEO watchers note — lilyraynyc · 2026-10-19
- Perplexity says it contributed to NVIDIA's Nemotron 3.5 mid-training, more coming — inductionheads · 2026-10-19