Skip to main content

GPT 5.1 Instant has trouble completing - UX bug or model issue?

Bug Reports

I’ve been trying the new GPT 5.1 option, and I’ve noticed that sometimes when I prompt, the model gets stuck and repeats the last token several times before timing out. Not sure if this is a problem with the model itself or T3’s custom UX. Example screenshot included. I’m not 100% sure, but I think it’s more common on mobile browser than desktop.

Status: Investigating / Needs Repro2 comments

This request was merged into another request

Comments2

  • Mark Florkowski

    Team

    Appears to be a model issue, we have raised it with our contacts at OpenAI to hopefully get some clarity.

  • Aquamarine Butter

    I was in fact able to replicate several times in Chrome 142 on Windows 11. The chat is here, you can see it glitches out and repeats a token containing the word “real” several times before ending:

    https://t3.chat/share/sv307peudl