Anthropic says Fable 5.2 solved two open theoretical physics problems
Anthropic says Fable 5.2 solved two open theoretical physics problems
According to Anthropic, Fable 5.2 nearly autonomously completed calculations for two long-standing open problems in theoretical physics, including black-hole formation in small anti-de Sitter universes.
Anthropic also said that Fable 5.2 solved two open theoretical physics problems
The first problem, related to black holes, had been open since 1983. At that time, scientists showed that when anti-de Sitter universes are heated, black holes appear abruptly, like water boiling. However, their method worked only for large universes where relativity applies. For very small universes, where only a quantum description remains, the calculation was outlined in 2003, but it was too labor-intensive and no one completed it. Fable 5.2 almost autonomously finished this calculation and found that in small universes the transition is also abrupt.
The second problem is related to a method scientists have actively used for 15 years to screen candidates for quantum gravity theories in a simplified universe model. The question about the exact limit of this method's applicability remained open, and Fable 5.2 found it for the first time.
The math part is done — now theoretical physicists may be out of a job.
Why it matters
AnalysisIf these results are confirmed, it could show that AI can not only assist with computations but also finish scientific tasks that have remained open for decades.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Another Anthropic engineer builds an OS with Fable 5.2
Another Anthropic engineer created an operating system using Fable 5.2, spending 8 days of continuous work and running more than 1,000 subagents.
Anthropic engineer creates AAA-level result using Fable 5.2
According to the author, an Anthropic engineer used Fable 5.2 to create content that already resembles high-budget AAA games.
Claude Haiku (Fast Compact Models by Anthropic)
The most compact and fastest model in the Anthropic lineup, designed for lightning-fast responses, mass text classification, data extraction, and agent routing at minimal cost.
Claude Opus (Flagship AI Model by Anthropic)
The most powerful heavyweight model in the Anthropic family, designed for complex philosophical and scientific analysis, multi-layered text generation, and deep contextual understanding.