Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Boomerang - protocol to dissolve some commitment races, published by Filip Sondej on May 30, 2023 on The AI Alignment Forum.

Work done during SERI MATS 3.0 with mentorship from Jesse Cliffton. Huge thanks for all the feedback and discussions to Anthony DiGiovanni, Daniel Kokotajlo, Martín Soto, and Rubi J. Hudson! Also posted to EA forum.

Daniel's post about commitment races motivates why they may be a severe problem. Here, I'll describe a concrete protocol that if adopted, would let us avoid some cases of miscoordination caused by them.

TL;DR

The key ingredient is having a mandatory time delay, during which the commitments aren't yet binding. At the end of that delay, you decide whether to make your commitment binding or revert it, and this decision can be conditional on previous decisions of other participants. This in itself would give rise to new races, but it can be managed by adding some additional rules.

I think the biggest challenge would be to convince the "commitment infrastructure" (which I describe below) to adopt such a protocol.

Benefits

In the case of the game of chicken, the 3 rules listed below should often push whoever committed later to Swerve.

In simple games like chicken it may be achieved easier, just by relying on conditional commitments (“If I came second, I Swerve”). But here we add another mechanism: tentative commitment period, which gives us another nice feature:

In the real world it can be not so obvious that some commitments are incompatible. The tentative period gives the agents time to analyze the situation in depth and check if any commitments are clashing. This is especially useful in highly multipolar cases where multiple parties try to commit at the same time or where actions have complex consequences and interactions.

We also don't need to know in advance all the actions the others can take - we can analyze their actions after they've already tentatively committed to them.

Even if participants manage to coordinate (so one Dares and one Swerves), the solution found hastily during a commitment race can still be quite poor. Boomerang enables bargaining that can Pareto improve on this hasty solution.

Necessary ingredients

The protocol relies on some mechanism M on which agents can make commitments - a "commitment infrastructure". M could be something like the Ethereum network, or some powerful international body.

We require that:

When someone publishes a commitment, M arrives at a consensus about the time at which the commitment was published.

It’s more convenient/cheap/credible to do some commitments on M that outside of it.

2. is needed because the protocol relies on certain commitments being forbidden. Agents could decide to do those forbidden commitments outside of M, so we need to make that as hard as possible for them, compared to committing on M. I think this is the hardest part of the whole proposal. M would need to be locked into place by a network effect - everyone is using M because everyone else is using M.

Protocol

Here are the rules:

R1: All commitments have a mandatory tentative period, meaning that they only become binding after some fixed time T (we can say that freeze_time = publish_time + T).

So you have no way to make a commitment credible before freeze_time (if you were allowed to end the tentative period, we would create a new race to end the tentative period as soon as possible).

R2: During the tentative period, you can still decide to revert your commitment.

Somewhere before the freeze_time you send to M your final decision (whether you revert or not), but hashed.

You also need to add random salt to your decision before hashing, so that it cannot be revealed through brute-forcing.

After freeze_time you reveal the decision (and it must match the previously sent hash, otherwise M would reject your commitment).

So...