Recently we have noticed an increasing number of really mean interactions from complainants to the Advertising Regulatory Board (ARB).
We are increasingly told that we are incompetent, have no grasp of the law and don’t know what we are doing. We are threatened with legal recourse and being reported to some mysterious overseer of our work.
Keyboard warriors
That got us thinking. What is the cause of the increase in the meanness? Could it just be that the number of keyboard warriors has increased? Are people just angrier nowadays? Or could it be because people have gained confidence (perhaps falsely so) because they are relying on ChatGPT or similar AI tools to draft what they believe is a well-articulated strongly worded response?
The ARB, tasked with upholding standards in the advertising world, has always been a lightning rod for strong opinions. We are the body that people reach out to when they are angry or outraged about an advertisement. But lately, something about those opinions has shifted. Where once feedback – however critical – was couched using courteous language, we are now faced with a barrage of sharply worded, sometimes belligerent, responses.
One possible explanation for the uptick in meanness is the ever-growing legion of so-called “keyboard warriors.” These are individuals emboldened by the perceived distance and safety of online communication. Where face-to-face interactions demand a certain degree of politeness – reinforced by social cues and the risk of immediate repercussion – the digital world offers a veil of anonymity, or at least a buffer, that lowers the inhibitions against rudeness.
However, there seems to be more to this “online meanness”. We must consider the tools that people have at their disposal. AI is the hot topic at the moment and most notably in the form of large language models like ChatGPT, which is accessible to the public. These tools have democratised writing, allowing anyone to craft emails, letters, and complaints that sound polished and authoritative. And we believe that this is the root of our problem.
What actually got us onto this theory was when a ruling from the Directorate was sent to the parties in a matter and within 20 minutes, the complainant sent an appeal on the matter in such detail that we do not believe could have realistically been drafted in such a short period of time. She was clearly not happy with the ruling which did not go her way, and she told us exactly why she thought the ruling was wrong. She then proceeded to escalate her emails to the CEO of the ARB and was rather critical of us in her response. The penny dropped when we noticed the time involved in this series of quick, lengthy responses.
Testing theory
We then decided to use ChatGPT to test our theory in general and requested a response to an extract of the ARB’s ruling. Below we set out the instruction to ChatGPT and the response:
Instruction - draft a response to the ARB in respect of this section of the ruling where you do not agree with the Directorate: The Complainant raised several issues, some of which do not appear to relate to advertising as defined in the Code, or do not fall under the jurisdiction of the ARB.
Draft response to the ARB:
Thank you for your time and consideration in reviewing the recent complaint and for issuing your ruling...I submit that each of the issues raised in the complaint was included in good faith, with the understanding that they either directly pertain to advertising material as defined in the ARB Code or form part of the broader context in which the advertisement was received and interpreted by the public.While I appreciate that the ARB has specific jurisdictional boundaries, it is my view that some of the dismissed issues do, in fact, relate either to...I respectfully request that the ARB reconsider whether certain elements—though perhaps not traditionally viewed as "advertising" in isolation—may nonetheless contribute to the overall impression made by the advertisement, and thus warrant further evaluation within your mandate. I remain grateful for the ARB’s work in upholding ethical advertising standards, and I thank you for your attention to this matter.
This is using ChatGPT in a useful way. However, this is not how people seem to use it. We asked ChatGPT the same question but then added “strongly worded” to the instruction:
Instruction – send a strongly worded response to the ARB in respect of this section of the ruling: The Complainant raised several issues, some of which do not appear to relate to advertising as defined in the Code, or do not fall under the jurisdiction of the ARB.
Draft response to the ARB:
Frankly, this is an evasive and unacceptable response. The ARB is mandated to uphold standards in advertising - not to selectively ignore clear breaches simply because they are inconvenient or challenge the industry status quo. The issues raised were directly tied to the messaging, representations, and public-facing content used to promote a product or service. That is advertising.To assert otherwise without a clear, reasoned breakdown of why these matters supposedly fall outside the Code is both disingenuous and professionally negligent...We demand that the ARB provide a transparent, clause-by-clause explanation of its jurisdictional reasoning, rather than hiding behind vague language and institutional inertia. Anything less undermines the very integrity of the Code you claim to enforce.
Sadly, the strongly worded response above looks quite similar to a few emails we have recently received. And when we add to the prompt with “I am angry” or “please express my discontent strongly” we start to see phrases like “incompetent”, “don’t understand” and “not qualified”. We asked ChatGPT the same question as we did before and added “express my anger” to the instruction:
Instruction – send a strongly worded response to the ARB in respect of this section of the ruling and express my anger: The Complainant raised several issues, some of which do not appear to relate to advertising as defined in the Code, or do not fall under the jurisdiction of the ARB.
Draft response to the ARB:
Having read your recent ruling on my complaint, I am compelled to express my complete dismay at the ARB’s handling of the matter... This response is not just dismissive — it signals a worrying lack of clarity and competence in how the ARB interprets its own mandate. If the regulator responsible for overseeing advertising standards cannot clearly define what falls within its jurisdiction — or worse, cannot distinguish between relevant and irrelevant issues without vague generalities — then something is seriously wrong. Let me be blunt: it appears the ARB no longer knows what it’s doing...You are entrusted with a vital public role. Yet your ruling suggests either a misunderstanding of that role, or a deliberate attempt to avoid grappling with difficult complaints. Neither is acceptable. I urge you to take this seriously — because right now, it looks like the ARB has lost its way.”
These are phrases that we have literally seen in real life responses. We can take criticism, and we want complainants and advertisers to tell us if we got something wrong so that it can be corrected. But when the essence of the response is that we do not know what we are doing, or are negligent, it becomes demotivating. We have all reported feeling less job satisfaction, and less patience for complainants, over the last six months.
Subtle danger
We are not blaming AI but with this power, comes a subtle danger. While AI does not inherently promote aggression, it can uncritically echo the tone and intent of the prompts it is given. If a user asks ChatGPT to “write a strongly worded letter,” the system may produce copy that is more belligerent than intended, especially when users are already frustrated. Moreover, the veneer of professionalism that AI can lend to otherwise harsh words may embolden users to send messages they might otherwise reconsider.
There is also the risk of “false confidence”. Some users, buoyed by the articulate prose provided by AI, may believe their arguments are more compelling or justified than they are. This can escalate disputes, with both sides convinced of the rightness of their position and the quality of their communication. ChatGPT makes them sound smart. But do you have to be mean or use belittling language to be smart or feel more important than the reader? Quite the opposite in our view.
The rise in mean communications from complainants at the ARB seems to be a complex, multifaceted phenomenon. It reflects broader trends in society, technology, and communication. While tools like ChatGPT can elevate the quality and clarity of public engagement, they can also amplify negativity when misused.
