Constructive mathematics does not accept the classical proof:https://en.m.wikipedia.org/wiki/Goodstein%27s_theorem
In mathematical logic, Goodstein's theorem is a statement about the natural numbers, proved by Reuben Goodstein in 1944, which states that every Goodstein sequence (as defined below) eventually terminates at 0.
Laurence Kirby and Jeff Paris[1] showed that it is unprovable in Peano arithmetic (but it can be proven in stronger systems, such as second-order arithmetic or Zermelo-Fraenkel set theory).
This was the third example of a true statement about natural numbers that is unprovable in Peano arithmetic, after the examples provided by Gödel's incompleteness theorem and Gerhard Gentzen's 1943 direct proof of the unprovability of ε0-induction in Peano arithmetic.
The Paris–Harrington theorem gave another example.
There is a lot of non-constructive proof in classical mathematics, not all of which have a constructive alternative.ChatGPT: What is the position of constructive mathematics on Goodstein's theorem?
Constructive mathematics, particularly in the tradition of intuitionism and constructive logic, generally does not accept the standard proof of Goodstein’s theorem as valid, because that proof relies on principles that are non-constructive—especially transfinite ordinals and classical reasoning about infinite sets.
Summary of the Issue:
Goodstein’s theorem states that every Goodstein sequence eventually terminates at zero, no matter the starting number. However, the standard proof of this theorem, developed by Kirby and Paris, uses transfinite ordinal numbers (specifically, up to ε₀), which are not constructively justified.
Why Constructivists Reject the Proof:
1. Use of non-constructive ordinals: The ordinal ε₀ is a transfinite ordinal whose use requires accepting the law of the excluded middle and completed infinities—both of which are generally rejected in constructive frameworks.
2. Lack of a constructive bound: The proof does not provide a computable or constructive method to determine how long a Goodstein sequence takes to reach zero.
3. Unprovability in Peano Arithmetic (PA): While the theorem is true and provable in stronger classical systems (like second-order arithmetic), it is unprovable in PA, and constructive mathematics is often more restrictive than PA in what it accepts.
Alternative Constructive Approaches:
Some constructive mathematicians have attempted to analyze fragments of the Goodstein sequences or construct alternative, weaker versions of the theorem that are provable without transfinite induction.
Others explore the computational aspects of the sequence (like recursive bounds), but these still fall short of a full constructive proof of termination.
In Summary:
Constructive mathematics does not accept Goodstein’s theorem as proven, at least not in the full generality of the classical result, because the standard proof uses non-constructive methods that are not permitted in constructive logic. It remains a good example of a theorem that is classically true but not constructively provable.
In my opinion, it may not always be possible to prove convergence of hyper-exponentially growing sequences by finitistic methods. It looks pretty much pointless to look for a finitary approach to decide the Goodstein problem. Therefore, I deem the infinitary method used in the proof to be an acceptable match for the problem at hand.
I reject the constructive objections to the classical proof and I accept Goodstein’s theorem as proven.