Please or to access all these features

Site stuff

Join our Innovation Panel to try new features early and help make Mumsnet better.

See all MNHQ comments on this thread

Odd AI-generated thread title options in Site Stuff

205 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

OP posts:
Error404FucksNotFound · Yesterday 11:01

Efacsen · Yesterday 10:49

Did your post contain M N Trolls - without the gap between the M and N?

That seems to trigger the automatic spam filter

no, it was the same as i posted after that, I just copied it into word and selected plain text only.

TemperanceWest · Yesterday 11:04

Morecoffeeneedef · Yesterday 11:01

Perhaps a new thread linking this one (with a meaningful title) would be useful. People need to know.

It would probably get deleted as a TAAT!

MrsBennetsPoorNervesAreBack · Yesterday 11:05

Morecoffeeneedef · Yesterday 10:59

The only person to have this code in their browser would be involved in generating AIBU posts for Mumsnet. You believe the OP's account of what happened, so who apart from Mumsnet could have been using that code and managed to post it in the Title field?

It would seem that MNHQ are effectively accusing @AmIAComplete of being a troll - why on earth would someone have this kind of code in their browser if they weren't deliberately seeking to generate AI posts?

But if @AmIAComplete was engaged in that kind of activity, then surely they would know about it and not post the code on MN?!

MrsBennetsPoorNervesAreBack · Yesterday 11:06

TemperanceWest · Yesterday 11:04

It would probably get deleted as a TAAT!

That's what I thought. Otherwise I would have already done it!

Morecoffeeneedef · Yesterday 11:07

MrsBennetsPoorNervesAreBack · Yesterday 11:05

It would seem that MNHQ are effectively accusing @AmIAComplete of being a troll - why on earth would someone have this kind of code in their browser if they weren't deliberately seeking to generate AI posts?

But if @AmIAComplete was engaged in that kind of activity, then surely they would know about it and not post the code on MN?!

Yes quite. @AmIAComplete would hardly advertise the fact if she was doing it. And why would she bother doing it anyway?

MrsBennetsPoorNervesAreBack · Yesterday 11:08

Morecoffeeneedef · Yesterday 11:07

Yes quite. @AmIAComplete would hardly advertise the fact if she was doing it. And why would she bother doing it anyway?

Exactly. None of it adds up!

MrsBennetsPoorNervesAreBack · Yesterday 11:08

What's the betting that this whole thread will get deleted at some point?!

Megifer · Yesterday 11:13

MrsBennetsPoorNervesAreBack · Yesterday 11:08

What's the betting that this whole thread will get deleted at some point?!

I dont think it'll be deleted tbf, they know that will effectively be admitting AI responses are generated.

I think theyre hoping it will just die off as the title does look a bit benign 😬

ShitFacedShakespeare · Yesterday 11:17

Megifer · Yesterday 11:13

I dont think it'll be deleted tbf, they know that will effectively be admitting AI responses are generated.

I think theyre hoping it will just die off as the title does look a bit benign 😬

OP can always ask them to edit the title 🤭

MrsBennetsPoorNervesAreBack · Yesterday 11:18

Megifer · Yesterday 11:13

I dont think it'll be deleted tbf, they know that will effectively be admitting AI responses are generated.

I think theyre hoping it will just die off as the title does look a bit benign 😬

Yeah, you're probably right.

It would seem that they have been well and truly rumbled though.

MrsBennetsPoorNervesAreBack · Yesterday 11:18

ShitFacedShakespeare · Yesterday 11:17

OP can always ask them to edit the title 🤭

Grin
TemperanceWest · Yesterday 11:19

MrsBennetsPoorNervesAreBack · Yesterday 11:18

Yeah, you're probably right.

It would seem that they have been well and truly rumbled though.

Agree.

MrsBennetsPoorNervesAreBack · Yesterday 11:20

We should keep posting on the thread to keep it near the top of active conversations. As many MNers as possible should be able to see the thread so that they can draw their own conclusions.

Error404FucksNotFound · Yesterday 11:28

It's not showing on trending so I expect it will die

MrsBennetsPoorNervesAreBack · Yesterday 11:29

Error404FucksNotFound · Yesterday 11:28

It's not showing on trending so I expect it will die

I presume that's what MNHQ will be hoping.

BellesAndGraces · Yesterday 11:40

The most straightforward answer is usually the correct one. If I hear hooves, I assume it’s a horse, not a zebra.

The obvious explanation is that Mumsnet is using, or testing, AI to generate responses to posts.

An entirely unrelated browser extension or keyboard app just happened to produce a MN-specific AIBU response prompt while someone was posting on Mumsnet … sounds a lot like a zebra to me.

Bloodysquirellls · Yesterday 11:42

Wow.

I don’t think this is a MN story.

Because that prompt has clearly been written by AI itself.

This is an AI gone rogue story 🫣

MNs AI is going to take over the world ☠️

Megifer · Yesterday 11:50

MrsBennetsPoorNervesAreBack · Yesterday 11:29

I presume that's what MNHQ will be hoping.

If they do then at least we'll know that it is true, they are definitely using AI/bots to respond to posts. The Walter White style explanation given makes no sense at all.

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.

JaneJeffer · Yesterday 11:53

Imagine how people are going to feel if they start a thread and even the Mumsbot doesn’t respond to them Sad

SwedishEdith · Yesterday 11:55

Bloodysquirellls · Yesterday 11:42

Wow.

I don’t think this is a MN story.

Because that prompt has clearly been written by AI itself.

This is an AI gone rogue story 🫣

MNs AI is going to take over the world ☠️

Ha ha but you were right.

JaneJeffer · Yesterday 11:56

There’s no need for an AI title generator @JustineMumsnet

MrsBennetsPoorNervesAreBack · Yesterday 11:59

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 , 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?

escapegoats · Yesterday 12:02

@JustineMumsnet could you not just get rid of the title generator? In my experience it throws up fairly poor suggestions anyway. But also it seems that in the process MNHQ don't really understand the broader implications and risks.

escapegoats · Yesterday 12:03

BellesAndGraces · Yesterday 11:40

The most straightforward answer is usually the correct one. If I hear hooves, I assume it’s a horse, not a zebra.

The obvious explanation is that Mumsnet is using, or testing, AI to generate responses to posts.

An entirely unrelated browser extension or keyboard app just happened to produce a MN-specific AIBU response prompt while someone was posting on Mumsnet … sounds a lot like a zebra to me.

Agreed!!

Swipe left for the next trending thread