An AI Outfit Promises Something Infinite: Er, Really? Infinite?
November 28, 2025
Another dinobaby original. If there is what passes for art, you bet your bippy, that I used smart software. I am a grandpa but not a Grandma Moses.
Venture Beat publishes some write ups that strike me like marketing collateral. I am not sure what to make of an article that asserts an “infinite” service. Let’s not skip over the idea of infinity. I think a couple of mathy types drove themselves crazy thinking about infinities of infinities working two ways: Bigger numbers and then smaller numbers. Yep, those close to these mathy types checked them into a facility for those sufficiently unusual. Would this article “Anthropic’s Claude Opus 4.5 Is Here” Cheaper, AI, Infinite Chats, and Coding Skills That Beat Humans (sic).”
Georg Cantor makes an appearance at the Happy Valley Rest Home. He tells the nurse delivering his scopolamine that he wants to talk about the central infinite-cardinality problem before he is placed in isolation. Thanks, Venice.ai. Close enough, although the setting does not look too much like a 19th century facility. Oh, well.
The first step on what will be a short journey I assure you. Let’s let Anthropic Claude 4.5 define “infinite”, shall we? Here’s the response:
Infinity represents unboundedness—a concept of endlessness without limit. In mathematics, it describes quantities exceeding any finite value or processes continuing indefinitely. Infinity isn’t a number but an abstract notion of limitlessness, fundamental to calculus, set theory, and cosmology.
Notice that Claude 4.5 did not mention marketing and PR speak. This is important for “Anthropic’s Claude Opus 4.5 Is Here: Cheaper AI, Infinite Chats, and Coding Skills That Beat Humans.” Note the two-word phrase “infinite chats.” Nope, I don’t think so. Not even Amazon’s money pipe can serve “infinite chats.” Come on, Claude. Get real. Amazon cannot even keep its system online if my memory serves me. But infinite? Hmmm.
The write up says that Venture Beat engaged in an exclusive interview with Alex Albert, “Anthropic’s head of developer relations.” (I think this means a marketing job. What do you think?) Here’s a statement that caught my attention:
The new model, Claude Opus 4.5, scored higher on Anthropic’s most challenging internal engineering assessment than any human job candidate in the company’s history, according to materials reviewed by VentureBeat. The result underscores both the rapidly advancing capabilities of AI systems and growing questions about how the technology will reshape white-collar professions. The Amazon-backed company is pricing Claude Opus 4.5 at $5 per million input tokens and $25 per million output tokens — a dramatic reduction from the $15 and $75 rates for its predecessor, Claude Opus 4.1, released earlier this year. The move makes frontier AI capabilities accessible to a broader swath of developers and enterprises while putting pressure on competitors to match both performance and pricing.
Does this strike you as what I caller a “better, faster, cheaper” approach. I like to add cheaper is the operative word. Yep, buy the market and raise prices later. Does this surprise me? No. From a company that promises to deliver something that costs money infinitely, cheaper does not surprise me one whit.
Here’s another statement I found interesting:
Albert said employee testers consistently reported that the model demonstrates improved judgment and intuition across diverse tasks — a shift he described as the model developing a sense of what matters in real-world contexts. “The model just kind of gets it,” Albert said. “It just has developed this sort of intuition and judgment on a lot of real world things that feels qualitatively like a big jump up from past models.”
To test this statement, I fired up Claude 4.5 again and asked, “Is it possible for a commercial enterprise supported by modest customer sales and venture capital to deliver an “infinite service”; for example, infinite chats for users?”
Here’s what the “just kind of gets it” Claude told me:
No, it’s not sustainably possible. Here’s why:
- Real Costs Scale with Usage: Every chat consumes computational resources (servers, energy, bandwidth). Even efficient models incur marginal costs per interaction that accumulate with heavy users.
- Finite Capital: Venture funding and modest sales provide limited runway. Without usage caps, a small subset of power users could drain resources disproportionately, making the business model unsustainable.
- Economic Reality: “Unlimited” offerings typically include hidden constraints (throttling during peak times, deprioritization, or eventual tier upgrades). True infinity would require infinite capital and infrastructure.
- Tragedy of the Commons: Without limits, rational users maximize personal use, collectively overwhelming the system—forcing either service degradation or imposed restrictions.
Practical Outcome: Most companies offer generous but capped services (e.g., “50 free messages/day”) or tiered pricing. Marketing terms like “unlimited” often mean “more than typical users need,” not literally infinite. Would you like examples of how AI companies balance accessibility with sustainability?
I think that Mr. Albert might want to check his assertions with his product that “infinite” is a tough promise. But let’s not stop with the infinite. What about this statement in the write up?
Opus 4.5 outscores all human candidates on company’s toughest engineering test.
For me, the sticking point is the word “all.” Categorical affirmatives are problematic. Black swans aside, “all” is a cousin of infinite. Its use implies a rather sweeping approach to those who take a tough engineering test. What’s the sample? One, 100, 10,000? Yeah. Oh, well.
What’s the proof? Here’s the chart that did not knock me over with shock. I know it is difficult to read. Navigate to the cited article on a boat anchor computer with a big screen, and you can sort of read the numbers. Look for this:
Claude 4.5 is better than also-rans like Google and OpenAI. Well, why not? Anthropic has whipped infinite and tamed all. Dealing with weak wristed systems like Googzilla and ChatGPT is trivial.
Mr. Albert offered a statement which Venture Beat uses to complete this remarkable feat of content marketing, hyperbole, and logical impossibilities:
When asked about the engineering exam results and what they signal about AI’s trajectory, Albert was direct: “I think it’s a really important signal to pay attention to.”
Yep, pay attention. I did.
Stephen E Arnold, November 28, 2025
Comments
Got something to say?
-
- Subscribe to Beyond Search
Feature archive
News archive
-
