Codex in GPT-5.5 Mode Keeps Calling Itself GPT-5 with Old Cutoff
CtrlAltDwayne · x · 2026-07-08
Users discovered that when OpenAI Codex is set to GPT-5.5 xhigh mode, it consistently identifies as GPT-5 in all new conversations and reports a knowledge cutoff of June 2024, contradicting its actual configuration. This reveals a discrepancy between the model's self-identification and its actual version settings, serving as a notable heads-up for developers using Codex.
More from Models
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11
- RoMa v2 image matching model unveiled in the usual black poster — ducha_aiki · 2026-09-11
- OpenAI rated Astra 'Critical' for cyber capabilities — and admits it's harder to monitor — theguywhobuilds · 2026-09-11