Transcript: OpenAI’s Altman Shows Ads Interest With Caveats

OpenAI CEO Sam Altman

Creative threat perception

With AI perceived as a threat to creatives, Financial Times looks at London-area creative agencies and the future impact of AI. The FT largely projects a defiant agency cohort and taps Mother:

“There is still a global role for London agencies. Felix Richter, Mother’s chief creative officer, argues that ‘America has the innovation but Europe has the craft: the attention to detail and nuance that makes something really original.’ Mother has offices in New York, Los Angeles, Shanghai and Berlin, while VCCP has five international offices including New York.”

Read more in Financial Times (June 24).


Stats: brand visibility in GenAI

The media and marketing world continues to spin on moving from SEO (search engine optimization) to GEO (generative engine optimization).

Joe Ciarallo, pr pro at Well Hub after stops at Salesforce and Toast, asked his LinkedIn followers yesterday what they’re doing to “impact brand visibility in GenAI overviews.”

He takes inspiration from the findings below by marketing intelligence platform, Ahrefs, which is trying to move its business from SEO to GEO.

Ahrefs

More: 80+ AI momentum stats (June 24) – Ahrefs

Snippet:

  • “The global AI market is worth $758B in 2025 (Precedence Research, June 2025)“

  • “Global gen AI spend is set to total $644B in 2025, up 76.4% on 2024 (Gartner, March 2025)“

  • “Global AI revenue stands at $30B in 2025–predicted to rise to $85B in 2029 (S&P Global, June 2025)…“

See all 80+ on Ahrefs.


playing catch up on AI

Cloud-based website building company Wix has quietly released a new AI marketing assistant, perhaps with good reason: it addresses SEO but not GEO -today’s hot new marketing tactic.

In an interview yesterday with TechRadar (which noticed the tool’s release) Wix head of analytics Doreen Weissfelner says the AI tool will “efficiently develop and implement marketing plans for SEO, social media marketing, email marketing, and paid ads all from one place.” Read more.

She adds that “it’s going to support GEO (generative engine optimization) tasks as well,” but no timeline is provided.

The space is moving fast and perhaps last week’s acquisition by Wix of eight-person AI coder Base44 for $80 million cash is an attempt by the $9 billion publicly-traded company to accelerate for the future.


Sam Altman on ads

In an OpenAI podcast published June 18, OpenAI CEO Sam Altman spoke at length on advertising and his company.

Hear it on Apple Podcasts [starts 16:15].

On advertising and Open AI:

(This transcript has been lightly edited for clarity.)

We haven’t done any advertising product yet. I’m not totally against it. I can point to areas where I like ads. I think ads on Instagram are kind of cool – I bought a bunch of stuff from them. But I think it would be very hard… it would take a lot of care to get right.

People have a very high degree of trust in ChatGPT, which is interesting because… “AI hallucinates” – it should be the tech that you don’t trust that much. (…)

But I think part of that is, if you compare us to social media or web search, where you can tell that you are being monetized and the company is trying to deliver you good products and services, no doubt, but also to get you to click on ads, how much do you believe that you’re getting the thing that that company actually thinks is the best content for you versus something that’s also trying to interact with the ads?… I think there’s a psychological thing there.

On ad product types:

For example, I think if we started modifying the output – like the stream that comes back from the LLM – in exchange for who was paying us more, that would feel really bad. And I would hate that as a user. I think that’d be like a trust-destroying moment.

Maybe if we just said, “We’re never going to modify that stream. But, if you click on something that is going to be what we’d show anyway, we’ll get a little bit of the transaction revenue, and it’s a flat thing for everybody… if we have an easy way to pay for it or something”… maybe that could work?

Maybe there could be like ads outside of the LLM stream that are still really great? But the burden of proof there, I think would have to be very high. And it would have to feel like really useful to users and really clear that it was not messing with the LLM’s output.

On purchasing through ChatGPT:

… That’s good if we can do it in some sort of really clear and aligned way. But I don’t know. I love that we build good services. People pay us for them. It’s very clear.

On Google search:

Google search was an amazing product for a long time. It does feel to me like it’s degraded, but there was a time where there were lots of ads, but I still thought it was the best thing on the internet. I mean, I love Google search. It’s clearly possible to be a good ad-driven company, and I respect a lot of things Google has done, but there are obviously issues too.

Subscribe to the OpenAI podcast.

And, see the podcast on X. (June 18)


The market speaks

Intel (INTC) Jumps 5% on AI Deal With Accenture to Slash Marketing Costs (June 24) – Yahoo Finance


Agentic advertising and IBM

IBM was touting its partnership with workflow company Mint[dot]ai yesterday on LinkedIn as “Big Blue” stakes out ground in “agentic advertising.”

Mint CEO Lorenzo Larini (prev. Gartner, Ipsos executive) discussed the news two weeks ago.

The IBM Partner Program hub explained yesterday on LI:

MINT is collaborating with IBM to bring agentic AI to advertising, transforming media operations with a multi-agent platform built on watsonx.

What to expect: This collaboration shifts the model from AI-assisted to agent-operated, enabling hybrid teams of humans and agents. Built to meet the compliance and complexity of today’s media landscape, the platform offers:

* Role-specific, compliant AI agents for advertising workflows
* Up to 30% fewer hours spent on media operations
* 30+ specialized agents targeted to launch in the next 90 days…

See a demo:Media Planning with Multi AI agents” from May on the IBM TechXchange website:

Mint
Screenshot

More:

  • IBM and MINT to Advance Agentic AI in Advertising. (undated) – Mint blog
  • Announcement on Larini’s arrival at Mint in early 2024 and a bit about Mint’s transition to an AI product line (January 2024) – press release
  • Mint funding overview – Pitchbook

Prompt: What are the bottlenecks in media planning that AI could fix for the advertising community within the next five years?

Response from Google search – AI mode:

AI holds the potential to address several bottlenecks in media planning and buying for the advertising community within the next five years. Here are some key areas where AI can offer significant improvements:

  1. Data Overload and Analysis:

Bottleneck: Media planners often struggle to make sense of the overwhelming volume of data from various platforms, reports, and sources. Gleaning actionable insights from this data can be time-consuming and challenging.

AI Solution: AI Data Analysts Agents can aggregate and analyze vast data sets to identify key trends, patterns, and anomalies in real-time, providing actionable insights for optimization. AI helps marketers find solutions by analyzing vast data sets to identify nuanced patterns in behavior, consumption, and intent.

  1. Fragmented Platforms and Silos:

Bottleneck: Planning across isolated platforms and channels can lead to fragmented strategies and missed opportunities for synergy.

AI Solution: AI Strategist Agents can take a unified view of all channels, breaking down silos and recommending an optimized media mix based on cross-platform data analysis.

  1. Budget Misallocation

Read the entire response on tipsheet.


AI enablement analysis

“Mark Zuckerberg stated on a recent episode of the Stratechery podcast that he expects advertising’s share of global GDP to grow as a result of AI enablement. Historically, advertising’s share of global GDP has remained relatively stable, between roughly 1.5-2.5%, depending on the measure…”

Read the full take from analyst Eric Seufert on X. He doesn’t agree with Mr. Zuckerberg.


Cannes AI exhaust

  • A tale of two Cannes: Has technology finally conquered creativity? (June 24) – Gerry D’Angelo on LinkedIn (D’Angelo is a former P&G VP of Media, now advises Mediaocean, McKinsey and others)

  • Onstage, execs hailed AI. Behind closed doors, the industry is grappling with the end of a ‘golden era’ (June 24) – Adweek

  • Video: “While you were at Cannes with the crumbling Media-Spindustrial Complex, I was with the future of marketing… at hashtag#Vidcon25!” (yesterday) – Randall Rothenberg, former IAB CEO on LinkedIn


More stuff

  • Google Faces UK Pressure Over AI Search Summary, Advertising (June 24) – Bloomberg (subscription)
  • This AI Startup (Springboards) Encourages Hallucinations For The Sake Of Creative Inspiration (June 24) – AdExchanger
  • Claude AI maker Anthropic bags key “fair use” win for AI platforms, but faces trial over damages for millions of pirated works (June 24) – AI Fray
  • New event: “CTRL+Create – Taking Control of Creativity In The Age of AI” – July 16, NYC – Rembrand
  • FTC Approves Omnicom-IPG Merger After Ad Giants Pledge Not to Boycott Over Politics (June 24) – The Wall Street Journal