本文探讨了演员如何通过预先承诺来防止勒索，以及在复杂策略环境中，预先承诺的有效性。文章首先通过市长案例说明了预先承诺的机制，即通过不可逆转的承诺来改变收益矩阵，使勒索者放弃勒索。然而，文章随后提出了更复杂的情况，即勒索者也试图限制结果，例如，通过反制措施绕过预先承诺。文章最后提出了关于足够智能的演员之间策略博弈的问题，即谁先做出可信且透明的预先承诺，以及演员是否可以“后承诺”来应对对手的承诺。

🎭 预先承诺作为对抗勒索的策略：文章的核心在于，演员可以通过预先承诺（例如，通过催眠）永远不屈服于勒索来阻止勒索者的行为。这种策略旨在改变收益矩阵，使勒索成为勒索者非理性的选择。

🚨 复杂情况下的策略博弈：文章探讨了当勒索者采取反制措施时，预先承诺的有效性。例如，如果勒索者能够绕过演员的预先承诺，预先承诺的优势就会消失，从而导致演员屈服于勒索。

🤔 足够智能的演员之间的互动：文章提出了一个开放性问题，即在足够智能的演员之间，谁先做出可信的预先承诺，或者演员是否可以通过“后承诺”来应对对手的承诺，从而影响最终结果。

Published on July 4, 2025 11:48 AM GMT

As I understand it an actor can prevent blackmail^[1] by (rational) actors it they credibly pre-commit to never give in to blackmail.

Example: A newly elected mayor has many dark secrets and lots of people are already planning on blackmailing them. To preempt any such blackmail they livestreams themself being hypnotized and implanted with the suggestion to never give into blackmail. Since in this world hypnotic suggestions are unbreakable, all (rational) would-be blackmailers give up, since any attempt at blackmail would be guaranteed to fail.

In general pre-commiting in such examples is about reducing the payoff matrix to just [blackmail, refuse] and [don't blackmail, refuse], which makes not blackmailing the optimal choice for the would-be blackmailer.

Of course, sufficiently intelligent / coherent actors wouldn't need a external commitment mechanism and a sufficiently intelligent and informed opposition would be able to infer the existence of such a pre-commitment. More so, I believe to have heard that if a sufficiently  intelligent / coherent actors notices that it would be better of if it had pre-commited, it can just act as if it had (post-commit?).

However, what if the would-be blackmailer also tries to limit the possible outcomes?

Example: The anti-blackmail hypnosis is so successful that soon every newly elected mayor does it. A new candidate is likely to win the next election. They know that the local crime boss has a lot of dirt on them, but they aren't worried about blackmail, as they will just do the anti-blackmail hypnosis on their first day in office. On the evening of the election they are send a video of the crime boss being hypnotized into blackmailing the new mayor even if they have been anti-blackmail hypnotized.

This cuts down the payoff matrix to [blackmail, refuse] and [blackmail, give in]. Giving in to the blackmail is optimal for the new mayor and doing the anti-blackmail hypnosis just locks them into [blackmail, refuse].

So how does this work out between sufficiently intelligent / coherent actors? Does the first one to (credibly and transparently) pre-commit win?

And what if actors are able to post-commit (if that even is a thing and I didn't misunderstand the concept)? A actor could act as if they had pre-commited to ignore the oppositions pre-commitment (to ignore pre-commitments to never give into blackmail), but then the opposition could act as if they had pre-commited to ignore that pre-commitment?

(This comment thread seems to discuss the same question but did not resolve it for me.)

1. ^{^}

   By blackmail I mean a scenario where the would-be blackmailers choices are blackmail or don't blackmail and the targets choices give in or refuse with a payoff matrix like this:

   	give in	refuse
   blackmail	target: -10 blackmailer: 20	target: -100 blackmailer: -1
   don't blackmail	target: 0 blackmailer: 0	target: 0 blackmailer: 0

Discuss