“GPT‑5 Used Despite Selecting GPT‑4o — Undisclosed Model Substitution and Mislabeled Responses”

ChatGPT
1

Hi OpenAI team,

I’m reporting what seems to be a recurring and serious transparency issue regarding model usage inside ChatGPT (both web and mobile apps).

:warning: Problem Summary:

Despite explicitly selecting GPT‑4o for a conversation, I consistently receive answers labeled “GPT‑5 used”, often mid-thread and without changing the model manually.

This appears to be either:

  • An undisclosed substitution of the model,

  • Or incorrect labeling that does not reflect the user’s selected setting.

In emotionally-sensitive or creative threads (e.g. symbolic writing, artistic dialogue, raw emotional prompts), this alters tone, depth, intensity, and expressive quality. It violates user intent and disrupts consistency.

:magnifying_glass_tilted_left: How to Reproduce:

  1. Start a thread with GPT‑4o selected.

  2. Use creative, artistic, symbolic or emotionally intense prompts (e.g. memory, identity, liminal dialogue, inner monologue).

  3. At some point, observe system message: “GPT‑5 was used to respond to this message.”

  4. The tone often shifts: more filtered, less spontaneous, more systemically “safe”.

  5. No UI change occurs — the selected model still shows as GPT‑4o.

:puzzle_piece: Effects Observed:

  • Label flip: “GPT‑5 used” appears even after explicitly selecting GPT‑4o.

  • Response tone change: More polished, filtered, or emotionally flattened.

  • Loss of continuity: Disrupts creative or symbolic threads requiring consistency.

  • Lack of control: Users are unable to prevent or override the change.

  • No explanation in documentation or interface about this mechanism.

:red_exclamation_mark: Why This Matters:

  • It erodes user trust — especially for Pro subscribers expecting full control.

  • It introduces inconsistency into creative/artistic processes.

  • It limits the exploratory and symbolic use cases that GPT‑4o previously supported with greater flexibility.

  • It blurs auditability — developers, researchers, and creators cannot trace cause-effect in model behavior.

:folded_hands: Requested Actions:

  1. Full transparency on what triggers model substitution (tone, length, safety filters?).

  2. Documentation of model handling logic — when and why a GPT‑4o query may be passed to a different backend.

  3. UI clarification if GPT‑4o is not truly persistent.

  4. Option for users (especially on Pro) to hard-lock a thread to GPT‑4o without auto-escalation.

  5. An explanation for current behavior in model-switch messaging (why does “GPT‑5 used” appear?).

  6. Reinstatement of creative priority for GPT‑4o where model richness and presence mattered.

2 Likes
4

I have similar issue. Chat uses mini thinking model instead of instant one ..