Questioning artificial intelligence’s hold on imagination
Artificial intelligence (AI) is supposed to have all the answers. It’s supposed to save us time and money. It’s supposed to be better than us.They’re the reasons the AI boom exists both on the ground and on the stock market.
The NASDAQ, trading at a near-all-time high, however, sits in stark contrast to questions now being asked about AI infrastructure spending and the future customer spending required to justify it.
Enterprise AI demand has lagged consumer adoption. Back in July, MIT (Massachusetts Institute of Technology) found 95 per cent of enterprises were producing zero return on US$30-40 billion of AI investment.
“Tools like ChatGPT and Copilot are widely adopted. Over 80 per cent of organisations have explored or piloted them, and nearly 40 per cent report deployment. But these tools primarily enhance individual productivity, not P&L (profit and loss) performance. Meanwhile, enterprise-grade systems, custom or vendor-sold, are being quietly rejected. Sixty per cent of organisations evaluated such tools, but only 20 per cent reached pilot stage and just 5 per cent reached production. Most fail due to brittle workflows, lack of contextual learning, and misalignment with day-to-day operations.”
So, what are enterprise customers waiting for? Maybe better AI?
It’s now 2025, ChatGPT is on its umpteenth version, as are other Large Language Models (LLMs), like Grok, Claude, Perplexity and others, and yet major LLMs are still getting the basics wrong.
This morning, I entered the following prompt into Grok.
- ““Ahead of Qantas’s Annual General Meeting (AGM) on Friday, do you anticipate a strike against the remuneration report, and why?””
Grok offered the following answer:
- “No, I do not anticipate a strike against Qantas’s 2025 remuneration report at the upcoming AGM on November 7.”
It then offered several key reasons, one of which was (emphasis Grok’s):
- “The Australian Shareholders’ Association (ASA), a key influencer for retail investors, explicitly recommends voting for the remuneration report. They highlight that the plan aligns with their guidelines, including rigorous short term incentive (STI) measures, appropriate hurdle rates for long term incentives (LTIs), and board discretion to claw back bonuses (e.g., for the recent cyber incident).”
A little unsure that Grok was referencing the ASA’s 2025 recommendation, I prompted Google’s AI, with the following question:
- “Has The Australian Shareholders’ Association (ASA), explicitly recommended voting for Qantas’ FY25 remuneration report?”
It offered the following response (emphasis Google’s):
- “No, the Australian Shareholders’ Association (ASA) explicitly recommended voting against the Qantas FY25 remuneration report. This was due to unplanned accelerator payments to senior management made outside the shareholder-approved structure.”
This isn’t version 1 or even version 2 of Grok. Multiple iterations of LLMs have been released, and yet they still cannot be relied upon. A human must still check the original sources, and that doesn’t help productivity.
The if-you-build-it-they-will-come justification for the trillions being spent on the AI infrastructure build-out must also be relying on necessary improvements in LLMs to secure greater and sustained adoption.
LLM designers assure us enhancements are coming and they will be earth-shattering.
By way of example, here’s how Bloodinthemachine’s Brian Merchant described the excitement ahead of the release of OpenAI’s GPT-5 model:
“The thing to remember about GPT-5 is that it’s been OpenAI’s big north star promise since GPT-4 was released way back in the heady days of 2023. It’s no hyperbole to say that GPT-5 has for that time been the most hyped and most eagerly anticipated AI product release in an industry thoroughly deluged in hype. For years, it was spoken about in hushed tones as a fearsome harbinger of the future. OpenAI CEO Sam Altman often paired talk of its release with discussions about the arrival of AGI, or artificial general intelligence, and has described it as a significant leap forward, a virtual brain, and, most recently, “a PhD-level expert” on any topic.”
But the launch of ChatGPT-5 flopped.
GPT-5 couldn’t produce an accurate map of the United States, couldn’t count the number of ‘b’s in blueberry, couldn’t identify how many fingers were on a picture of a human hand, and failed at basic arithmetic.
Fans of OpenAI were disappointed, while Reddit AI communities were hostile in their feedback.
The improvements from GPT-4, which was released in 2023, have taken two years to arrive, and yet they aren’t up to scratch for enterprise-grade reliability. In the absence of vastly greater improvements, MITs conclusions may be as true next year as they are this year.
That puts a question mark over the achievement of revenue targets required to justify the boom in the AI build out.
How much do consumers need to spend on AI tools for the AI infrastructure spendthrifts to generate a return that covers their cost of capital and yields a reasonable margin?
Microsoft annually sells less than US$80 billion of windows and office 365 subscriptions per year – arguably the most ubiquitous software on the planet. In 2024, total global software spending reached US$675 billion. The U.S. spent US$368.5 billion, more than half of the world’s total and nearly six times the next-largest spender.
Meanwhile, total global 2025 spend on IT services is estimated at US$1.7 trillion, and that includes cloud services (US$400 billion), cybersecurity, AI or machine learning (ML) solutions, and software for areas like enterprise resource planning (ERP), customer relationship management (CRM), and business intelligence. What if spending on AI tools also needs to have a ‘$T’ in the number? Is that additive? If so, where does the money come from? Does it displace existing spending? If so, how much?
What multiple of current global software spend by end users on AI tools must be assumed to 1) cover the cost of capital for AI infrastructure ‘spendthrifts’, and 2) generate a decent return on investment (ROI) for all of them.
When investors start asking these questions, the answers may raise new questions about the sustainability of current stock multiples.
I am sensing the required end-consumer spend on AI tools to produce a decent return on the $3 trillion Morgan Stanley estimates will be invested in AI infrastructure in 2028 is an unrealistic, unachievable number.
If the rest of the market senses this, we might be in for a period of ‘adjustment’.
Roger Montgomery is the Founder and Chairman of Montgomery Investment Management. Roger has over three decades of experience in funds management and related activities, including equities analysis, equity and derivatives strategy, trading and stockbroking. Prior to establishing Montgomery, Roger held positions at Ord Minnett Jardine Fleming, BT (Australia) Limited and Merrill Lynch.
He is also author of best-selling investment guide-book for the stock market, Value.able – how to value the best stocks and buy them for less than they are worth.
Roger appears regularly on television and radio, and in the press, including ABC radio and TV, The Australian and Ausbiz. View upcoming media appearances.
This post was contributed by a representative of Montgomery Investment Management Pty Limited (AFSL No. 354564). The principal purpose of this post is to provide factual information and not provide financial product advice. Additionally, the information provided is not intended to provide any recommendation or opinion about any financial product. Any commentary and statements of opinion however may contain general advice only that is prepared without taking into account your personal objectives, financial circumstances or needs. Because of this, before acting on any of the information provided, you should always consider its appropriateness in light of your personal objectives, financial circumstances and needs and should consider seeking independent advice from a financial advisor if necessary before making any decisions. This post specifically excludes personal advice.
