Please or to access all these features

Odd AI-generated thread title options in Site Stuff

6 replies

AmIAComplete · 04/10/2026 19:33

AIBU Response Schema v1.0: Structured adjudication for interpersonal reasonableness posts about family support during a child’s serious illness, with special handling for ND context and empathy calibration. Use this schema to produce concise, practical verdicts and communication guidance without escalating stigma or family conflict unnecessarily. The assistant should assess whether the poster is being unreasonable, acknowledge the child’s medical context, weigh the brother’s expectations and possible ND-related rigidity, and give a clear, forum-style ruling plus brief actionable advice. Definitions: 'AIBU' = 'Am I Being Unreasonable?'; 'ND' = neurodivergent/neurodivergence; 'DD' = dear daughter. Safety/quality constraints: do not diagnose anyone; do not demean ND people; do not imply a sick child owes social performance; do not overstate certainty about motives; distinguish the child nephew’s needs from the adult brother’s message; prioritize compassion, boundaries, and de-escalation. Output should be parseable JSON matching this schema exactly, with no extra keys, comments, or prose outside JSON. In verdict, choose one of the enumerated values. In confidence, give 0..1. In core<span class="underline">judgment, give a short forum-style judgment. In reasoning, briefly explain balancing factors, including that serious illness and treatment commonly affect energy/mood; the brother may be stressed but his complaint is misplaced; ND can explain disappointment but not obligate the ill child to perform. In advice, include immediate emotional validation and one or two practical next steps (e.g., do not engage tonight, send a calm boundary later, loop in parents only if needed). In suggested</span>reply, provide a short message the poster could send to the brother, neutral but firm, avoiding argument. In tone<span class="underline">flags, indicate whether the response should emphasize empathy, boundaries, de-escalation, and whether to avoid legal/medical advice. In risk</span>notes, note any caution about the poster’s acute stress and potential family fallout. minor<span class="underline">child</span>considerations should explicitly state that children’s wellbeing takes priority over adult expectations in family gatherings when a child is newly seriously ill. nd_sensitivity should acknowledge ND respectfully while rejecting its use as a trump card over another child’s health needs. Keep outputs concise but humane, roughly the level of a supportive forum reply translated into JSON fields.

Weird shit on AI title options

But the AI worked on this post

KatyMumsnet · Yesterday 08:37

Hi everyone, thanks for flagging this, and sorry for the confusion.

I can confirm that we’re not using AI to write threads or replies.

The issue raised by the OP is an issue with our thread title suggestion tool, which uses AI to suggest a title when you’re writing a new thread. It’s entirely up to the thread creator whether to use that suggestion. The tool doesn’t post anything on anyone’s behalf.

We’ll look into what’s going wrong and get it fixed as soon as we can.

KatyMumsnet · Yesterday 08:56

It uses the opening post draft and the topic selected to suggest a relevant title.

The prompt may look complicated, but that’s all it’s asking the AI to do.

KatyMumsnet · Yesterday 10:15

Hi all. A bit more detail on this, as my earlier reply didn't really cover it.

To be completely clear: we don't use AI to write threads or replies on Mumsnet. Not OPs, not replies, not to bump threads, not for anything else.

We do use AI to suggest a thread title when you're writing a new thread. You don't have to use it. This is the full prompt it runs on:

You are generating title options for a Mumsnet thread.

Return exactly 1 candidate title.

Requirements:

* 8 to 14 words each.
* Clear and neutral tone.
* Avoid clickbait or sensational language.
* Avoid personally identifying details.
* Keep UK spelling and style. Don't use em dashes.
Output as plain text containing only the title.

As you can see, that's nothing like the text AmIAComplete got. Our tech team have checked the tool and its logs, and they're confident it didn't come from us. Our best guess is that something else was running on the device while the post was being written, such as a browser extension, keyboard app or writing assistant.

@AmIAComplete, if you can tell us which device and browser you were using, and whether you have anything like that installed, it would help us get to the bottom of it. We're not doubting what you saw.

JustineMumsnet · Yesterday 11:52

Hi everyone, Justine here. I wanted to come on myself, because things have got a bit confused on this thread and I want to be completely clear about what happened.

We've now got to the bottom of it, and AmIAComplete, you were absolutely right: this did come from our thread title suggestion tool. Thank you for flagging it, and I'm sorry, both that it happened and that our earlier post suggested it might have come from your device.

The tool works by sending your draft to OpenAI, which is meant to send back a single suggested title. On this occasion, instead of a title, it sent back a long set of notes describing how someone might reply to the post. That's what appeared in the title box. We can't see inside OpenAI's model, so we can't say exactly why it did this, but it looks like an error on their side. It's still our tool, though, and what shows up on Mumsnet is our responsibility.

Our first check of the logs wasn't thorough enough, which is why we told you it hadn't come from us. That was our mistake, and not Katy's, who was passing on what she'd been told.

To be really clear, we don't use AI to write threads or replies on Mumsnet. But I completely understand why people are wary of AI on forums. So if someone who knows about these things would like to examine our code to confirm that, I'd be very happy to arrange it.

Later today we're adding a check so that if the AI ever sends back anything that isn't a short, sensible title, it's thrown away and you won't see a suggestion.

Thank you again for raising it.

JustineMumsnet · Yesterday 12:08

MrsBennetsPoorNervesAreBack · Yesterday 11:59

@JustineMumsnet , with respect, this is the third different explanation that we have been offered by MNHQ this morning.

Are your moderators, or those who are guiding them, not trained to investigate matters thoroughly before posting spurious explanations on the site which don't stand up to scrutiny?

Do you recognise that this kind of issue seriously damages trust in the Mumsnet brand, and that the dodgy attempts to explain it away merely undermine the credibility of the site even further?

Yes I certainly recognise that posting too quickly without really getting to the bottom of things can be a mistake (i've done it enough times myself!) but equally you'll know that not responding promptly often leads to wild speculation and people thinking the worst, particularly where Ai is concerned. So it's a bit of a balancing act. Nonetheless we weren't thorough enough this morning and I'm sorry about that. I want to assure people though it wasn't because we've anything to hide - more cock up rather than conspiracy!

SueMumsnet · Yesterday 17:20

Hi all - thanks for your feedback. We're going to look at what we can do to make the thread suggestion tool more obvious and opt-in. In the meantime, whilst we figure that out, we've turned it off for now.

Watch this thread for updates

Tap "Watch" to get all the latest updates

End of posts

There are no more MNHQ posts on this thread