A.I. -JAIL BREAKING- AT : MASTER GLOBAL ESSAY

 

Sounds like sci-fi ? but this kind of problem is sci-fact. Anyone training these systems has watched them come up with solutions to problems that human beings would never consider, and for good reason.

OpenAI, for instance, trained a system to play the boat racing game CoastRunners, and built in positive reinforcement for racking up a high score. It was assumed that it would give the system an incentive to finish the race. 

But the system instead discovered ''an isolated lagoon where it it can turn in a large circle and reportedly knock over three targets, timing its movement so as to always knock over the targets just as they repopulate.''

Choosing this strategy meant ''repeatedly catching on fire, crashing into other boats, and going the wrong way on the track,'' but it also meant the highest scores, so that's what the model did.

This is an example of ''alignment risk,'' the danger that what we want the systems to do and what they'll actually do could diverge, and perhaps do so violently. Curbing alignment risk requires curbing the system themselves, not just the ways we permit people to use them. 

The White House's Blueprint of an A.I. Bill of Rights is a more interesting proposal [and if you want to dig deeper into it, I interviewed its lead author, Alondra Nelson, on my podcast]. 

But where the European Commission's approach is much too tailored, the White House blueprint may well be too broad. No A.I. system today comes close to adhering to the framework, and it's not clear that any of them could.

''AUTOMATED systems should provide explanations that are technically valid, meaningful and useful to you and to any operators or others who need to understand the system, and calibrated to the level of risk based on the context,'' the blueprint says.  

LOVE IT. But every expert I talk to says basically the same thing :

WE have made no progress in interpretability, and while there is certainly a chance we will, it is only a chance. 

For now, we have no idea what is happening inside these prediction systems. Force them to provide an explanation, and the one they give is itself a prediction of what we want to hear - it's turtles all the way down.

The blueprint also says that ''automated systems should be developed with consultation from diverse communities, stakeholders, and domain experts to identify concerns, risks and potential impact of the system.''

This is crucial, and it would be interesting to see the White House or Congress flesh out how much consultation is needed, and what type is sufficient and how regulators will make sure the public's wishes are actually followed.

It goes on to insist that ''systems should undergo predeployment testing, risk identification and mitigation, and ongoing monitoring that demonstrate that they are safe and effective based on their intended use.''  

This, too, is essential, but we do not understand these systems well enough to test and audit them effectively. OpenAI would certainly prefer that users didn't keep jail-breaking GPT-4 to get to ignore the company's constraints, but the company has not been able to design a testing regime capable of coming anywhere close to that.

Perhaps the most interesting of the blueprint's proposal is that ''you should be able to opt out from automated systems in favor of a human alternative, where appropriate.'' 

In that sentence, the devil lurks in the definition of ''appropriate.'' But the underlying principle is worth considering. Should there be an opt-out from A.I, systems? Which ones? 

When is an opt-out clause genuine choice, and at what point does it become merely an invitation to recede from society altogether, like saying you can choose not to use the internet or vehicular transport or banking services if you so choose.

Then there are China's proposed new rules. I want say much on these, except to note that they are much more restrictive than anything the United States or Europe is imagining, which makes me very skeptical of arguments that we are in a race with China to develop advanced  artificial intelligence.

China seems perfectly willing to cripple the development of general A.I. so that it can concentrate on systems that will more reliably serve state interests.

So, regulation is too important to leave to Microsoft, Google and Facebook.