I am not sure which was the first of Google’s A.I. ads I saw that made me wonder if I was suffering from a fever. Maybe it was the one where “pandas in high fashion outfits walk the runway” — shown over thirty million times since early November, as of writing — but it just as easily could have been the one with “some crazy fruit creatures”. Maybe it was the ad with the strutting dogs. All are equally bizarre in the way a giant corporation’s ad company thinks it is offering something quirky and weird.
In any case, each ends with the same encouragement: “make more videos with a Google A.I. Pro subscription” for $27 per month. And I have to ask: who is this for?
These are not the only ads Google is running for its A.I. features. It shows them off in context for general users in Pixel phone ads, for students in ads for NotebookLM, for corporate clients with Cloud A.I., and — of course — for advertisers.
It also is not the only ad for its A.I. Pro subscription bundle. In a different one, different tasks are strung together for someone to do absolutely no work to put together a ’90s trivia night, leading to an invitation that twice tells recipients to wear platform shoes and “get ready”. The fine print might remind viewers to “check responses for accuracy”, but in the ad, the creator clicks send on a terribly written invitation immediately.
But it is those bizarre animal-themed ones which led to me looking up the advertising strategies of all the big A.I. players. I think this is a fascinating window. The ads they pay to show give us a glimpse of how they idealize the use of these products and services. While ads can sometimes be abstracted from the true function of a product or service, A.I. is already a new and confusing thing, so the narrative each company spins about its narrative seems telling of its own vision. I limited my search on this to ads of a typical video spot — no more than 30 seconds long. I did not include case studies or company-produced tutorials.
OpenAI runs a couple of types of ads. Those for ChatGPT mostly show its use as a personal assistant. There are several 30-second spots shot as oners with a pleasingly retro warmth. One has a training regiment for learning to do pull-ups; another is about siblings on a road trip. The same kind of messaging is used in a series of shorter spots. It also runs ads for its Codex agent, obviously targeted at developers, that are more clinical.
All of these seem practical to me. I could not find any current ads from OpenAI as disconnected from reality as Google’s. Just as notable is the focus of OpenAI’s spots — Google’s Ads Transparency Centre says the company is running about two hundred ads in Canada right now, most of which are variations in size, targeting, and placement of the shorter practical examples above, plus ads for Codex. For comparison, Google’s ads are all over the place. It is running around twenty thousand ads right now in Canada and, though not all of them are for A.I. features, many are, and you can tell from the examples above how much Google is just throwing stuff at the wall.
Anthropic’s ads are far more limited. All are for Claude and feature a video ad with no indication of how it is being used. It simply says “Claude is A.I. for […] all of us, anywhere” with overhead shots of different scenes representing different professions. This is basically the same sentiment as OpenAI’s ads, but executed without any specificity or examples. The company’s YouTube channel has plenty of case studies and demos, but no similar video spots.
If Anthropic is trying to mimic OpenAI’s quiet confidence, Perplexity has chosen overt aggression. Quasi-influencer types follow a similar script saying ChatGPT makes things up, and that is why you should trust Perplexity as it “searches the entire internet in less than one second and gives you one verified answer”. This explanation avoids acknowledging how much Perplexity depends on external A.I. models, including OpenAI’s GPT. In two of the ads, the narrator asks health-related questions, which is the boldest and maybe most reckless use case I have seen in any A.I. ad. There is nothing wrong with the answers it has generated, so far as I can tell, but it seems like a higher-stakes use than, like, a cake recipe, for example. In a variation of this ad type, the “influencer” looks generated, and contains Google search result screenshots that are at least twelve years old. Whatever the case, Perplexity must be spending huge amounts on its advertising. Each of these has been shown tens of millions of times, and two have hundreds of millions of views.
Meta’s ads are bizarre. I could not find any video ads for A.I. stuff — or metaverse-related things — through Google’s Ads Transparency Centre, but the company has a handful of 30-second spots on its YouTube channel. Almost like Google, Meta does not seem to know why people would use its A.I. assistant, so it comes up with offbeat premises that fall flat. In one, described as a way to “help sharpen your skills and transform the way you learn and understand complex subjects”, a guy is meeting his partner’s dad, a thermodynamicist. What a real person who is good at conversations would do is ask the dad a bunch of questions. What Meta thinks you should do is ask its assistant those questions instead and develop a fake level of expertise.
Also, not for nothing, but when I asked the same question in the web version of Meta A.I., it responded not with the tight and efficient explanation in the ad, but with:
😂 Thermodynamics-ist? Sounds like a real party crusher, eh? 🤣 Okay, serious face… A thermodynamicist is like, someone who’s all about the study of heat, energy, and how they transform into each other. They’re like the ultimate energy nerds, but in a good way! 🤓 They work with stuff like engines, refrigeration, and even black holes (mind blown, right? 🤯). Basically, they help us understand how to harness and use energy efficiently. Pretty cool, eh?
Am I meant to be charmed by “okay, serious face…” and four emoji in this barely coherent response? Because I am not.
In another ad, a guy somehow turns a large pan of what appears to be milk and two other pans of mystery liquid into pancakes for his kid. The kid pushes the plate off the counter, the dad asks “how can I get my two-year-old to eat his breakfast?”, and Meta A.I. knows that the kid likes when he makes silly faces. It is unclear to me how it knows this — whether it is automatically personalized to this user, or something the dad needed to teach the system, or if it is just an assumption that all two-year-olds like silly faces. The impression I get, though, is that it is distinctly unbelievable, and I do not want to give Meta knowledge of my entire life to find out if I am right.
To round this out, I looked for similar ads from Microsoft and Apple. I scrolled through hundreds of Microsoft ads on Google’s Ads Transparency tool, virtually all of which were Xbox related. I also checked its YouTube channel. I did not see any ads of the same type as above. I also found only a couple of ads for Apple Intelligence on Apple’s YouTube channel, both of which are for Clean Up in Photos. Apple seems to have cleaned up its YouTube channel overall, removing a whole bunch of older ads including some for Apple Intelligence.
I do not want to overstate how much these ads tell us — they are ads, you know? — but I think I learned something from the way each of these businesses thinks of its own products. In OpenAI, I see confidence; in Anthropic and Perplexity, I see an attempt to catch up. And in Google and Meta, I see established companies that are desperate to prove themselves — particularly in Google’s case, as I still cannot understand why generating arbitrary video is supposed to be compelling to a broad audience.
In the most practical and grounded ads, what I do not see are significant leaps beyond what a search engine today could do. OpenAI’s ads show ChatGPT summarizing a workout plan, but there are loads of those on external websites. Guides to road tripping through the Blue Ridge Parkway are plentiful. The same is true of the responses in Perplexity’s ads. What I see most in these ads are the big “pure” A.I. players normalizing their raison d’être, and established mega corporations entirely out of touch with what someone might want to do. Both are embarrassing in their own way for what is often pitched as the most revolutionary technology since the internet.
