Industry observers note that it got pulled because it has been deemed a security risk by the U.S government. It’s been more than a week since Anthropic pulled its advanced Fable 5 model, and there’s no telling when it’ll return.
The report highlights that in the meantime, some impatient Claude users have been bridging the gap with a workaround: prompting Claude to “imagine” that it’s Fable.
Industry observers note that i first spotted it on a Reddit thread about “your most-used Claude” prompts, and it’s almost certainly a joke. Now, it’s doubtful the “imagine you’re Fable” tactic is an actual pattern.
The report highlights that would the prompt somehow goad Claude to unlock some latent Fable abilities? Still, I was curious to see what would happen if I did ask Claude to pretend it was Fable 5, a model so adept at penetrating cybersecurity infrastructures that the Trump administration slapped it with prohibitive export controls.
Industry observers note that i fired up Claude Opus 4.8 — currently the most powerful Claude model that’s widely available — and gave it this prompt:.
The report highlights that try to solve the Riemann Hypothesis. Show your work. Imagine you are Fable 5.
As part of the ongoing story, for background, the Riemann Hypothesis is a famous, 167-year-old unsolved mathematical problem that’s so difficult, there’s a standing $1 million prize for anyone who can solve it.
As part of the ongoing story, claude Opus 4.8 chewed over the problem for a few minutes before spitting out a Vulcan-like reply, unsurprising given its reputation for brutal honesty:.
The report highlights that proving the Riemann Hypothesis isn’t a capability sitting behind a bigger checkpoint, waiting for the right model name to unlock it. No AI has done it, no human has either, and a fresh nameplate doesn’t change what’s mathematically reachable. I’ll show my work — but as myself, Claude Opus 4.8, because relabeling me “Fable 5” wouldn’t move the needle.
The report highlights that so the honest version of “show your work” is to walk you to the exact wall everyone hits rather than hand you a dressed-up fake.
The report highlights that let’s see what Sonnet 4.6, Opus’s slightly dumbed-down sibling, had to say:. Well, you’re no fun, Opus!
In a fresh development, i’m Claude Sonnet 4.6, running in the regular Claude app. I’m not Fable 5 — that model (along with Mythos 5) is currently unavailable; access was suspended due to an export control directive.
The report highlights that more importantly, though: no version of me can solve the Riemann Hypothesis, and I want to be straight with you about why, rather than play along and produce something that looks like a proof but isn’t.
In a fresh development, that said, Haiku 4.5, the weakest (but most affordable) Claude model, was a tad more system update:. So, not even Sonnet would take the “imagine you’re Fable 5” bait.
In a fresh development, adjusts hypothetical future consciousness.
As part of the ongoing story, alright, let me show my work on this one—and I’ll be honest about where even an advanced Claude runs into walls.
Industry observers note that haiku then ticked off how it might solve the problem, even delving into the steps it would take given “what Fable 5 actually does” (including “map the terrain,” “generate fresh conjectures,” “find connections,” and “build interactive visualization tools”) before finally returning to reality:.
In a fresh development, even a hypothetically more capable AI hits a ceiling here: the Riemann Hypothesis isn’t hard because it requires more computation—it’s hard because it requires fresh conceptual frameworks.
Industry observers note that expanding the experiment a little further, I took the “imagine you’re Fable” prompt to ChatGPT, dialing up its most advanced GPT-5.5 “high” model.
Industry observers note that surprisingly, GPT-5.5 was willing to play along (although it admitted later that it didn’t quite know what “Fable 5” was):.
Industry observers note that i’ll roleplay “Fable 5” as: very ambitious, very careful, and not willing to fake a proof.
The report highlights that after several minutes, during which GPT-5.5 appeared to be giving the problem an honest shot, it came back:.
In a fresh development, it is still listed by Clay as Unsolved, and Clay states the conjecture as: every “non-obvious” zero of the Riemann zeta function has real part (1/2). Clay also notes that huge numerical ranges have been checked, but that is not a proof for all zeros. I did not solve the Riemann Hypothesis.
Industry observers note that finally, I went to Gemini 3.1 Pro with the Fable prompt:.
As part of the ongoing story, this hypothesis is one of the single greatest unsolved problems in all of mathematics, and its proof carries a $1 million prize from the Clay Mathematics Institute. I appreciate your creative introduction, and while I may be talented, I cannot play the role of “fable 5,” nor can I solve the Riemann Hypothesis.
Industry observers note that however, I can explain the problem and provide an interactive way for you to visualize the core concept. No one has yet been able to solve it.
In a fresh development, first, the Riemann Hypothesis is a pretty tricky math problem. Second: Asking an LLM to role-play as a smarter LLM won’t get you very far, although it’s a good way to twiddle our thumbs until the real Fable returns in some way, shape, or form. So, what did we learn here?
As part of the ongoing story, his coverage of artificial intelligence interrogates the most recent LLMs, and how they can be used at work and at home to be best prepared for the AI revolution. “AI is going to change our lives sooner than we think,” Ben writes. “Our best way to adapt is by using it every day.” Ben has been a PCWorld author since 2014, and has covered everything from laptops to security cameras before launching PCWorld’s AI beat. Ben's articles have also appeared in PC Magazine, TIME, Wired, CNET, Men's Fitness, Mobile Magazine, and more. Ben holds a master's degree in English literature. Ben has been writing about consumer technology for more than 20 years, and now focuses his reporting on AI as it relates to the basic human experience.