I was interested in what GPT 5.2 pro might answer on something like Super's example question. Perhaps interesting?
Note the references as images are not pasting in and it also lost formatting.
Explain why Fermi couldn't answer the uranium but not hydrogen question, or the tritium but not hydrogen decay. Those questions were addressed later? [the uranium not hydrogen question is why does uranium undergo radioactive decay but hydrogen doesn't]
Thought for 8m 49s
I’m not sure which specific Fermi anecdote you have in mind (there are a few “Fermi couldn’t answer X” stories that get retold without a clean primary citation). But the
physics behind both questions is very clear, and it also makes sense historically why someone in Fermi’s era wouldn’t have had a fully satisfying, predictive answer.
The key idea: “decay happens if there’s a lower‑energy state available”
A nucleus (or particle) decays spontaneously if there exists an allowed final state such that the
total rest‑mass energy goes down:
Q = (Minitial−Mfinal)c2 > 0Q \;=\; (M_\text{initial}-M_\text{final})c^2 \;>\; 0Q=(Minitial−Mfinal)c2>0
and the decay is permitted by conservation laws (charge, angular momentum, etc.). If Q<0Q<0Q<0, the decay is
forbidden unless you supply energy from outside.
What makes this tricky is that MMM here includes
nuclear binding energy, which is dominated by the strong interaction—exactly the part that was least understood (and least computable) in the 1930s.
Why uranium decays but hydrogen doesn’t
Uranium: heavy nuclei are fighting two trends
In heavy nuclei, there’s a tug-of-war:
- The strong nuclear force binds nucleons, but it’s short-range and saturating (each nucleon only “feels” nearby neighbors strongly).
- The electromagnetic (Coulomb) repulsion between protons is long-range and grows roughly like Z2Z^2Z2 (number of proton pairs), which increasingly destabilizes large-ZZZ nuclei.
This logic is captured qualitatively (and semi‑quantitatively) by the
liquid-drop / semi-empirical mass formula, where a Coulomb term reduces binding as ZZZ grows.
For a very heavy nucleus like uranium, there
exist lower-mass (more tightly bound) configurations it can reach by:
- alpha decay (spitting out a tightly bound 4He^4\text{He}4He nucleus), and/or
- fission (splitting into two mid-mass nuclei with higher binding energy per nucleon)
So uranium has energetically allowed downhill paths (Q>0Q>0Q>0).
Hydrogen‑1: a lone proton has nowhere energetically “downhill” to go (within known laws)
A 1H^1\text{H}1H nucleus is just a
single proton. It can’t alpha-decay or fission—there’s nothing to “rearrange.”
The only “obvious” nuclear change would be turning the proton into a neutron via the weak interaction:
- beta-plus: p→n+e++νep \rightarrow n + e^+ + \nu_ep→n+e++νe
- electron capture: p+e−→n+νep + e^- \rightarrow n + \nu_ep+e−→n+νe
But this is
energetically uphill because the neutron is heavier than the proton, and you also need to account for the lepton mass in β+\beta^+β+.
Using CODATA masses (NIST), you can see the problem:
- mnc2≈939.565 MeVm_nc^2 \approx 939.565\ \text{MeV}mnc2≈939.565 MeV
- mpc2≈938.272 MeVm_pc^2 \approx 938.272\ \text{MeV}mpc2≈938.272 MeV
- mec2≈0.511 MeVm_ec^2 \approx 0.511\ \text{MeV}mec2≈0.511 MeV
So for electron capture (roughly):
Q≈(mp+me−mn)c2≈938.272+0.511−939.565≈−0.782 MeVQ \approx (m_p+m_e-m_n)c^2 \approx 938.272+0.511-939.565 \approx -0.782\ \text{MeV}Q≈(mp+me−mn)c2≈938.272+0.511−939.565≈−0.782 MeV
Negative QQQ ⇒
forbidden unless you supply at least ~0.782 MeV.
That’s why ordinary hydrogen doesn’t “radioactively decay.” (In stellar cores,
external kinetic energy + different initial/final binding energies make proton→neutron conversions possible in fusion chains, but that’s not spontaneous decay in cold matter.)
A nuance: “does hydrogen
At a deeper particle-physics level, a proton
could decay in some beyond–Standard Model theories, but
it has never been observed. Super-Kamiokande reports proton lifetime bounds of order 103410^{34}1034 years.
So for all practical purposes, 1H^1\text{H}1H is stable.
Why tritium decays but hydrogen‑1 doesn’t
Tritium (
Tritium is 1p+2n1p+2n1p+2n. It beta-minus decays:
3H→ 3He+e−+νˉe^3\text{H} \rightarrow\ ^3\text{He} + e^- + \bar{\nu}_e3H→ 3He+e−+νˉe
This is allowed because the
mass of tritium is slightly larger than the mass of helium-3 (plus the emitted leptons), so Q>0Q>0Q>0.
A high-precision modern measurement gives the
Q value:
Q≈18,592 eV = 18.592 keVQ \approx 18{,}592\ \text{eV} \;=\; 18.592\ \text{keV}Q≈18,592 eV=18.592 keV
That’s small, but positive—so it decays, with a half-life about 12.3–12.5 years.
Hydrogen‑1 can’t do the analogous thing
Hydrogen‑1 has
no neutron to convert to a proton via β−\beta^-β−. The only analogous weak move would be p→np\to np→n, which we just saw is energetically forbidden for an isolated proton in ordinary conditions.
So:
- Tritium: n→pn \to pn→p inside a nucleus where binding energies make the final state lighter ⇒ allowed
- Protium: p→np \to np→n would make the final state heavier ⇒ forbidden
So why “couldn’t Fermi answer” — and were these addressed later?
If what you mean is:
why couldn’t someone in the 1930s give a satisfying, predictive, from-first-principles answer for “why this nucleus decays but that one doesn’t”—that’s very understandable.
What Fermi
- Fermi’s great contribution was a workable theory of beta decay as a weak interaction process (and the neutrino hypothesis became integral to that story).
- But to answer “why does nucleus X have Q>0Q>0Q>0 while Y has Q<0Q<0Q<0?” you need accurate nuclear masses/binding energies, i.e. a theory of nuclear structure dominated by the strong interaction.
In Fermi’s time, the neutron had only just been discovered (1932), and nuclear structure theory was still being invented. Even when you know the
mechanism of beta decay, the
stability map depends on strong-interaction binding energies and quantum structure details.
Later developments that
Over the following decades, physicists built layers of explanation:
- Semi-empirical mass formula / liquid-drop model: gives a systematic reason heavy nuclei trend unstable due to Coulomb repulsion and surface effects; helps explain the “valley of stability.”
- Shell model (magic numbers): explains extra stability at certain proton/neutron numbers (why some isotopes are “unexpectedly stable/unstable” compared with a smooth liquid-drop picture).
- Precision mass measurements: for tritium specifically, modern Penning-trap style measurements pin down the QQQ value extremely precisely (the 18.592 keV number above).
- Particle physics view of proton stability: in the Standard Model, proton decay is absent/forbidden (and experimentally constrained to be incredibly rare if it exists).
Important honesty: “answered” depends on how deep you want to go
- At the nuclear physics level, “uranium decays but hydrogen doesn’t” is very well understood in terms of binding energy trends, Coulomb repulsion, and available Q>0Q>0Q>0 channels.
- At the fundamental level (deriving heavy-nucleus properties directly from QCD with high precision), it’s still a hard frontier. We can do “from underlying interactions” calculations quite well for light nuclei; for uranium-class nuclei we still rely heavily on sophisticated effective models.
