\(
\def\cuberoot#1{\sqrt[3]{#1}}
\def\fourthroot#1{\sqrt[4]{#1}}
\def\abspartial#1#2#3#4{\left|\,{\partial(#1,#2)\over\partial(#3,#4)}\,\right|}
\def\absdeltal#1#2#3#4{\left|\,{\d(#1,#2)\over\d(#3,#4)}\,\right|}
\def\dispop#1#2{\disfrac{\partial #1}{\partial #2}}
\def\definedas{\equiv}
\def\bb{{\bf b}}
\def\bB{{\bf B}}
\def\bsigma{\boldsymbol{\sigma}}
\def\bx{{\bf x}}
\def\bu{{\bf u}}
\def\Re{{\rm Re\hskip1pt}}
\def\Reals{{\mathbb R\hskip1pt}}
\def\Integers{{\mathbb Z\hskip1pt}}
\def\Im{{\rm Im\hskip1pt}}
\def\P{\mbox{P}}
\def\half{{\textstyle{1\over 2}}}
\def\third{{\textstyle{1\over3}}}
\def\fourth{{\textstyle{1\over 4}}}
\def\fifth{{\scriptstyle{1\over 5}}}
\def\sixth{{\textstyle{1\over 6}}}
\def\oA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obX{\rlap{$X$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obY{\rlap{$Y$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obZ{\rlap{$Z$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obc{\rlap{$c$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obd{\rlap{$d$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obk{\rlap{$k$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\oba{\rlap{$a$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obb{\rlap{$b$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt}
\def\obw{\rlap{$w$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt}
\def\obz{\overline{z}}\kern.5pt}
\newcommand{\bx}{\boldsymbol{x}}
\newcommand{\by}{\boldsymbol{y}}
\newcommand{\br}{\boldsymbol{r}}
\renewcommand{\bk}{\boldsymbol{k}}
\def\cuberoot#1{\sqrt[3]{#1}}
\def\fourthroot#1{\sqrt[4]{#1}}
\def\fifthroot#1{\sqrt[5]{#1}}
\def\eighthroot#1{\sqrt[8]{#1}}
\def\twelfthroot#1{\sqrt[12]{#1}}
\def\dis{\displaystyle}
%\def\definedas{\equiv}
\def\bq{{\bf q}}
\def\bp{{\bf p}}
\def\abs#1{\left|\,#1\,\right|}
\def\disfrac#1#2{{\displaystyle #1\over\displaystyle #2}}
\renewcommand{\ba}{\boldsymbol{a}}
\renewcommand{\bb}{\boldsymbol{b}}
\newcommand{\bc}{\boldsymbol{c}}
\newcommand{\bh}{\boldsymbol{h}}
\newcommand{\bA}{\boldsymbol{A}}
\newcommand{\bB}{\boldsymbol{B}}
\newcommand{\bC}{\boldsymbol{C}}
\newcommand{\definedas}{\equiv}
\newcommand{\half}{\frac{1}{2}}
\newcommand{\bsigma}{\boldsymbol \sigma}
\newcommand{\abs}[1]{\left|\,#1\,\right|}
\newcommand{\Rectangle}{\sqsubset\!\sqsupset}
\newcommand{\rectangle}{{%
\ooalign{$\sqsubset\mkern3mu$\cr$\mkern3mu\sqsupset$\cr}%
}}
\)
Feynman, Deutsch & Quantum Computing
Patrick Reany
8 August 2025
Patrick:
Is it a matter of record how Feynman "knew" in 1981 that quantum phenomena could enhance computation the beyond classical capabilities?
Copilot:
Yes, it is very much a matter of record how Richard Feynman came to propose in 1981 that quantum phenomena could enhance computation beyond classical capabilities. His insight was laid out in his keynote address at the First Conference on the Physics of Computation at MIT, later published as "Simulating Physics with Computers" in the International Journal of Theoretical Physics (1982).
Feynman's Reasoning in 1981
Feynman's core observation was this:
"Nature isn't classical, dammit, and if you want to make a simulation of nature, you'd better make it quantum mechanical."
Here's how he arrived at that conclusion:
- Classical simulation of quantum systems is inefficient: Feynman noted that simulating quantum systems on classical computers requires exponential resources. For example, simulating a system of $n$ quantum particles requires tracking $2^n$ complex amplitudes---an impossible task for large $n$.
-
Quantum systems evolve via unitary transformations: He proposed that a computer built from quantum mechanical principles could naturally simulate quantum systems by mimicking their unitary evolution.
-
Local interactions and cellular automata: Feynman was interested in models where computation arises from local interactions, like cellular automata. But he realized that classical automata couldn't capture quantum behavior such as entanglement and superposition.
-
Proposal of a quantum simulator: He didn't initially envision a general-purpose quantum computer, but rather a quantum system engineered to simulate other quantum systems. This idea laid the groundwork for quantum computation as a field.
Historical Context
Feynman's talk was revolutionary because it flipped the question: instead of asking how to simulate quantum physics on classical machines, he asked whether quantum systems could themselves be harnessed for computation. This was a conceptual leap that inspired later developments:
David Deutsch (1985) formalized the idea of a universal quantum computer.
Peter Shor (1994) showed that quantum algorithms could outperform classical ones for specific tasks like factoring.
Why It Mattered
Feynman's insight wasn't just a clever observation---it was a foundational shift. He recognized that quantum mechanics wasn't just a challenge for computation; it was an opportunity. His proposal reframed quantum weirdness (superposition, entanglement) as computational resources.
Patrick:
Okay, but it seems that Feynman wasn't presenting a blueprint on how to proceed, but that he was running off at the mouth on intuition --- not that that's bad, if you've got a good intuition. But before that 1981 address, Feynman was a very detailed physicist.
Copilot:
You're absolutely right, Patrick---and your instinct to distinguish Feynman's 1981 intuition from his earlier, more detailed work is spot-on. That keynote address was not a blueprint but a provocation, a speculative leap grounded in physical insight rather than formal construction. Feynman himself admitted as much in the opening lines of his talk:
"On the program it says this is a keynote speech---and I don't know what a keynote speech is... I have my own things to say and to talk about... So what I want to talk about is what Mike Dertouzos suggested that nobody would talk about."
Feynman's Shift in Style
Before 1981, Feynman was known for his meticulous work in quantum electrodynamics, statistical mechanics, and path integrals. His lectures and papers were rigorous, often grounded in calculation and physical modeling. But in this talk, he was doing something different:
- Speculative and playful tone: He openly rejected the idea of a formal keynote and instead riffed on ideas inspired by Ed Fredkin and cellular automata.
- Philosophical curiosity: He asked whether nature itself could be simulated by a universal computer---not just approximated numerically, but mimicked exactly.
- Intuition over formalism: He didn't present a model of a quantum computer, nor did he define qubits or gates. He simply observed that classical computers struggle to simulate quantum systems, and that perhaps quantum systems could do better.
What Did He Actually Know?
Feynman's intuition was based on a few key observations:
- Exponential complexity of quantum systems: He knew that classical simulation of quantum states scales poorly.
-
Quantum mechanics as unitary evolution: He understood that quantum systems evolve in ways that classical bits cannot emulate.
-
Local interactions and cellular automata: He was intrigued by the idea of computation arising from local rules, but realized that classical automata couldn't capture quantum behavior.
He didn't know how to build a quantum computer, nor did he claim to. But he did know that quantum mechanics offered a fundamentally different computational substrate---and that was enough to spark a revolution.
Feynman's Genius Here
What makes this moment so Feynmanesque is that he wasn't afraid to speak from intuition, even in the absence of a formal framework. He trusted the physical insight that quantum systems are hard to simulate classically, and flipped the problem: maybe quantum systems could simulate themselves.
Would you like to explore how this kind of intuition-driven leap compares to your own approach in developing spinor-based formalisms? There's a fascinating parallel in how both challenge inherited structures and seek deeper, more geometric clarity.
Patrick:
So, David Deutsch was the next link in the chain that eventually led to QC. Was he tying up loose ends as was Bell on the question of local realism?
Copilot:
Yes---David Deutsch's 1985 paper "Quantum theory, the Church-Turing principle and the universal quantum computer" was the next major step after Feynman's 1981 talk, and it did more than tie up loose ends. It formalized the intuition Feynman had gestured toward, and in doing so, Deutsch laid the theoretical foundation for quantum computation as a rigorous discipline.
But your analogy to Bell is quite apt. Like Bell, Deutsch was motivated by deep foundational questions---especially about the nature of reality, locality, and computation. Here's how their roles compare:
Deutsch's Leap
Deutsch’s 1985 paper did several things:
- Extended the Church-Turing principle: He argued that any physical process should be simulable by a universal computing device, but classical Turing machines fail to simulate quantum systems efficiently.
-
Defined the quantum Turing machine: This was the first formal model of a general-purpose quantum computer.
-
Linked computation to physics: He treated computation not just as an abstract process, but as something grounded in physical law.
Like Bell, Deutsch was driven by dissatisfaction with the conceptual foundations of quantum theory. But while Bell focused on measurement and locality, Deutsch focused on universality and simulation.
Loose Ends?
You could say Deutsch was tying up the loose ends of Feynman's intuition---but he was also opening new doors. Feynman asked "Can we simulate quantum physics with a computer?"
Patrick:
Deutsch seems to be absent from any significant QC development after he got it going. He left it to Shur and Grover and others to continue what he had started. He must have had more important things on his mind, or did he contribute more on the abstract side of things? [Actually, he did make further contributions to the field, as we shall see.]
Copilot:
Exactly---Deutsch didn't vanish from the scene, but he did pivot. After his foundational 1985 paper, he contributed several key theoretical advances, then gradually shifted toward deeper philosophical terrain. He wasn't chasing hardware or algorithms like Shor and Grover; instead, he was probing the conceptual bedrock of what computation is.
Deutsch's Post-1985 Contributions
Here's a brief map of his trajectory after launching quantum computation:
- 1989: Quantum computational networks --- laid groundwork for quantum circuits and gate-based models.
-
1992: Co-developed the Deutsch-Jozsa algorithm with Richard Jozsa --- one of the first quantum algorithms to show exponential speedup over classical counterparts.
- 1995: Collaborated with Artur Ekert and others on quantum logic gates and universality proofs, helping define what it means for a quantum computer to be "universal."
- Quantum error correction: Contributed to early thinking on how to preserve quantum information despite decoherence.
- Constructor theory (2012 onward): A radical rethinking of physics in terms of what transformations are possible or impossible, rather than what happens. This is his current focus.
So, the key difference that distinguishes classical computing systems from quantum computing systems is that the latter uses entanglement, right?
Yes, entanglement is one of the key features that distinguishes quantum computing from classical computing---but it's not the only one. Let's break it down:
Why Entanglement Matters
Entanglement allows quantum computers to link qubits in such a way that the state of one instantly affects the state of another, even across large distances. This leads to:
- Massive parallelism: Entangled qubits can represent and process many states at once.
- Quantum speedups: Algorithms like Shor's and Grover's exploit entanglement to outperform classical counterparts.
- Quantum communication: Enables protocols like quantum teleportation and quantum key distribution.
But entanglement alone doesn't make a quantum computer. It's the combination of superposition, entanglement, and unitary evolution (via quantum gates) that gives quantum systems their edge.
Afterword: