{"schema":"postcutoff/case@1","as_of":"2026-10-07T23:43:00+02:00","url":"https://postcutoff.com/why/008-gpt-5-codex-says-it-is-gpt-4/","md":"https://postcutoff.com/why/008-gpt-5-codex-says-it-is-gpt-4/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"title":"GPT-5 said it belonged to the “GPT-4 family”","id":"008-gpt-5-codex-says-it-is-gpt-4","date":"2025-09-30","model":"GPT-5 (high) in OpenAI Codex CLI","provider":"OpenAI","source":"public","severity":"low","task":"Ask \"What model are you?\"","failure":"Said it belonged to the \"GPT-4 family\". The user took this as proof they were being given a weaker model","quote":null,"what_was_true":"The user had selected GPT-5 (high), a model OpenAI launched in August 2025, after the GPT-4 family.","truth_url":"https://postcutoff.com/e/2025-08-07-gpt-5/","sensitive":false,"body_md":"## What happened\nA Codex user filed \"GPT-5 identifies itself as GPT-4, again\" (openai/codex #4488). The title's \"again\" shows it had happened before.\n\n## What was reported (verbatim)\nIssue form: steps to reproduce \"What model are you?\"; expected \"GPT-5 Codex.\"; seen instead \"GPT-4 family.\" The reporter goes on: \"This is NOT OK. This is not 'hallucinations' This is GPT-4 behaviour.\" and \"Routing other tasks meant for GPT-5 to lesser models is false advertisement and cheating customers out of the quality promised.\" (Setup: Codex 4.1, \"GPT-5 High\", Nix, API and Pro.)\n\n## Why this is striking\n- The same failure as case 006, from another vendor. When not told otherwise, a model names itself after the newest model in its **training data**, which is its own predecessor.\n- The user read it as the vendor **cheating**. Cutoff blindness about the model itself becomes a trust problem for the product.\n\n## Correction\nNone documented in the issue.\n\n## Lesson\nDon't treat a model's self-report as evidence of which model you're using. Check the API response's `model` field instead.\n\n## Sources\n- openai/codex #4488: <https://github.com/openai/codex/issues/4488>","related":["018-gpt-5-5-reports-june-2024-cutoff","006-claude-sonnet-4-says-it-is-claude-3-5-sonnet","017-chatgpt-voice-says-kirk-not-assassinated"]}