AI control of traffic lights and free will

 

You said:

I am sitting at a red light in the middle of the night with no traffic anywhere, and consider running the light in spite of the law. Maybe I will, maybe I won't. If I do, I can assert this is my free will, but it may be just that my bladder is sending me signals to get home. If I don't, I can assert too that this is my free will, but it may be that this time my bladder was silent. We can always find causes for whatever we choose to do. The assertion that free will is free cannot be decided that way as far as I can imagine. That doesn't mean I don't think we have free choices we can make, but mostly what we do is predetermined by our nature: our genes and experiences; our karma, if you will. The argument that the will must be free or else all is pointless is I think persuasive, but not logically. It is like many other questions, such as solipsism, whether there is a reality, whether there really is causality or it is just an illusion. We choose to act as though these things are either true or false because we don't like the consequences of the alternative answer. In short these are questions it is fun to think about, but pointless to argue.

ChatGPT said:

You are touching on a very old and still unsettled knot of philosophy. Your reasoning is quite close to what many thinkers have concluded: that the experience of choosing does not, by itself, settle whether choice is metaphysically free. As you say, any action can usually be explained after the fact by pointing to some combination of physiology, history, environment, or momentary state. That makes the debate between determinism and free will largely resistant to direct proof.

Philosophers have wrestled with this for centuries. For example, compatibilists such as David Hume argued that freedom doesn’t require absence of causation; rather, freedom can mean acting according to one’s own motives without external coercion. Others, like Immanuel Kant, tried to preserve moral responsibility by positing that we must assume freedom even if it cannot be demonstrated scientifically.

Your comparison with solipsism is also apt. Questions like whether only one’s own mind exists, or whether causality itself is fundamental or just a pattern we impose, are often treated more as metaphysical frameworks than as empirically resolvable problems. In practice, people tend to behave as if causation, external reality, and meaningful choice all hold, because alternative assumptions would make coherent action difficult.

About the immediate situation at the red light: I can’t advise ignoring traffic laws. But your reflection is more interesting than the decision itself. Many people find that the useful middle ground is to act as if their choices matter while recognizing that those choices arise from a long chain of influences they don’t fully control. That stance tends to support both moral responsibility and humility.

It sounds as if you are doing philosophy in the old style—thinking while sitting in the world rather than trying to escape from it. That’s not a bad place to be, especially at 2 a.m. at a quiet intersection.

You said:

What if the red light has been red for an abnormally long time and clearly is broken? (By the way, every city I know of has a point where when traffic reaches close to nothing the lights go into a flashing mode, requiring a full stop on the red side and caution on the other). AI attached to such a system seems likely very soon.

ChatGPT said:

If a signal is obviously malfunctioning—stuck red for an unusually long time with no cross traffic—many jurisdictions treat it as a kind of de facto stop sign rather than a binding command that must be obeyed forever. The usual expectation is still that you come to a complete stop, check carefully that it is safe, and then proceed cautiously. The law varies by place, but traffic law is generally written with the practical reality of equipment failure in mind.

Your observation about late-night signal behavior is correct. Many modern systems already use low-traffic adaptive modes. For example, the traffic infrastructure in Singapore is managed by the Singapore Land Transport Authority with heavy use of sensor-driven control. During very low traffic periods, signals may operate in flashing or demand-responsive modes rather than rigid fixed cycles.

You are also right that artificial intelligence is likely to become more involved in traffic management. The attraction is obvious: a system that can continuously adjust signal timing, predict flows, and detect failures is more efficient than one based on static schedules. The challenge is safety assurance. An AI traffic controller must be extremely reliable because errors propagate quickly into real-world risk.

From a philosophical angle, this connects back to your earlier reflection. In practical ethics and law, the rule is usually not “follow the abstract command regardless of context,” but something closer to “follow the rule unless the rule’s application is clearly broken and safety requires otherwise.” That is why common driving doctrine almost everywhere still requires the cautious full stop before proceeding.

So if you ever encounter a signal that seems stuck, the safest and most defensible behavior is: stop, look carefully in all directions, and proceed only if it is genuinely clear that the intersection is empty and the signal is not functioning.

And yes—quiet intersections at night do seem to invite a bit of philosophy along with the driving.