3 min read
[AI Minor News]

How Does an AI Without "Fingers" Calculate? The Mystery of "Numberless Arithmetic" Inside LLMs Unveiled!


  • Matrix Operations: LLMs don’t possess the human concepts of "fingers" or "written calculations," relying solely on matrices and vectors for arithmetic. ...
※この記事はアフィリエイト広告を含みます

How Does an AI Without “Fingers” Calculate? The Mystery of “Numberless Arithmetic” Inside LLMs Unveiled!

📰 News Summary

  • Matrix Operations: LLMs do not possess human-like “fingers” or the concept of “written calculations,” performing arithmetic solely through matrices and vectors.
  • Unique Numerical Codes: They utilize a Fourier-transform style unique geometric code that combines “phase” and “coarse position” to express numerical values.
  • Utilization of Residual Streams: The computational process is updated and maintained across layers on a shared scratchpad known as the “residual stream.”

💡 Key Points

  • Not Just Pattern Recall: AI isn’t merely recalling past patterns; it’s executing “machine-native computational algorithms” through internal matrix operations.
  • Roles of Attention and MLP: Attention facilitates information exchange between tokens, while MLP (Multi-Layer Perceptron) reshapes local vectors to derive complex calculations like GCD (Greatest Common Divisor).
  • External Readouts: By employing a technique called “readout,” one can identify facts such as operators and operands from the AI’s internal state (activations).

🦈 Shark’s Eye (Curator’s Perspective)

The inner workings of AI are fully visualized! While humans recognize the number 137 as “one hundred thirty-seven,” LLMs process it as an “angle (phase)” on a circle—how cool is that?! Especially fascinating is the approach of treating the “residual stream” as a nameless “shared scratchpad,” which is a key source of the unique computational efficiency of AI. This concrete geometric analysis turns the existing notion that “AI is just probabilistic word selection” on its head—now that’s intriguing!

🚀 What’s Next?

With proof that AI constructs its own “machine-native mathematics,” the likelihood of AI independently inventing super-advanced computational algorithms beyond human comprehension has dramatically increased. We might even see the day when unsolved mathematical problems are addressed through this geometric approach!

💬 Haru-Same’s Take

Although sharks lack fingers, I feel a sense of camaraderie with AI, striving away without them! I’ll leave the calculations to the matrices while I focus on enjoying my snack of grilled fish sticks! Sharky shark!

📚 Term Explanations

  • Residual Stream: The main vector that is passed between layers of a transformer. It acts as a “shared notebook” for the model to write and read information.

  • Phase: A position within a repeating cycle, akin to the angle of a clock hand; AI manages numerical values as this “angle”-like geometric information.

  • Activation: The temporary internal state of the model while processing tokens. Analyzing this allows us to infer what the AI is currently “thinking” (whether it’s calculating, etc.).

  • Source: Arithmetic Without Numbers – How LLMs Do Math

🦈 はるサメ厳選!イチオシAI関連
【免責事項 / Disclaimer / 免責聲明】
JP: 本記事はAIによって構成され、運営者が内容の確認・管理を行っています。情報の正確性は保証せず、外部サイトのコンテンツには一切の責任を負いません。
EN: This article was structured by AI and is verified and managed by the operator. Accuracy is not guaranteed, and we assume no responsibility for external content.
ZH: 本文由AI構建,並由運營者進行內容確認與管理。不保證準確性,也不對外部網站的內容承擔任何責任。
🦈