Most clinical trials are very simple statistical models. There are not trillions of parameters in a complex neural network architecture. Yet they are still the most effective tools we have at validating and optimising health and recovery in human beings. Very simple statistical tools can lead to large effects and,...
This is in itself a relatively benign failure mode no? Obviously in practice if this happened it may just be re-tried until it fails in a different mode or fail catastrophically on the first try
Hmm, I mean when we are talking about these kind of counterfactuals, we obviously aren't working with the wavefunction directly, but that's an interesting point. Do you have a link to any writings on that specifically?
We can perform counterfactual reasoning about the result of a double slit experiment, including predicting the wavefunction, but perhaps that isn't quite what you mean.
An interesting point here is that when talking about future branches, I think you mean that they are probabilities conditioned on the present. However as a pure measure of existence, I don't see why it would need to be conditioned on the present at all. The other question is then, what would count as WW2? A planetary conflict that has occured after another planetary conflict? A conflict called World War 2?
Perhaps you are talking about branches conditioned on a specific point in the past i.e. the end of WW1 as it happened in our past. In which case, I don't see why you couldn't estimate those probabilities, though it's a super complex and chaotic system which you would be applying estimates to and therefore best to take with a pinch of bayesian salt imo.
They are a tiny part of the search and development of an intervention.
I agree that there is complexity in healthcare that is not explained by a simple statistical model, my point is that the final layer often is a simple statistical model that drives a lot of the complexity and the outcomes. Making a drug is much more complex than deciding which drug to give, but that decision ultimately drives the outcomes.
Also incorrect. It would almost certainly require a complex model to find/create that content, possibly anew for each susceptible human.
Same point as above. If there were a piece of content that worked for all humans then a simple model would suffice (multi-armed bandit for example) and if the content doesn't exist, people are incentivised to create it
Most clinical trials are very simple statistical models. There are not trillions of parameters in a complex neural network architecture. Yet they are still the most effective tools we have at validating and optimising health and recovery in human beings. Very simple statistical tools can lead to large effects and, if misaligned, very large harms.
When private companies use A/B tests on human beings, they are usually explicitly optimising for objectives which are not aligned with human wellbeing - engagement, click-through rate, company profits. The harm that this can then cause depends on the nature of the interaction surface between the technology and the human, and the amount of exposure.
In configuration space we... (read 253 more words →)
I see, that's a great point, thanks for your response. It does seem realistic that it would become political, and it's clear that a co-ordinated response is needed.
On that note I think it's a mistake to neglect that our epistemic infrastructure optimises for profit which is an obvious misalignment now. Like facebook and google are already optimising for profit at the expense of civil discourse, they are already misaligned and causing harm. Only focusing on the singularity allows tech companies to become even more harmful, with the vague promise that they'll play nice once they are about to create superintelligence.
Both are clearly important and the control problem specifically deserves a tonne of dedicated resources, but in addition it would be good to have some effort on getting approximate alignment now or at least better than profit maximisation. This obviously wouldn't make progress on the control problem, but it might help society move to a state where it is more likely to do so.
"The EA consensus is roughly that being blunt about AI risks in the broader public would cause social havoc."
I find this odd and patronising to the general public. Why would this not also apply to climate change? Climate change is also a not-initially-obvious threat, yet the bulk of the public now has a reasonable understanding and it's driven a lot of change.
Or would nuclear weapons be a better analogy? Then at least nuclear weapons being publicly understood brought gravity to the conversation. Or could part of the reason to avoid public awareness be avoiding having to bear the weight of that kind of responsibility on our consciences? If the public is clueless,... (read more)
I agree, it still wouldn't be strong evidence for or against. No offence to any present or future sentient machines out there, but self-honesty isn't really clearly defined for AIs just yet.
My personal feeling is that LSTMs and transformers with attention on past states would explicitly have a form of self-awareness, by definition. Then I think this bears ethical significance according to something like the compression ratio of the inputs.
As a side note, I enjoy Iain M Banks representation of how AIs could communicate emotions in future in addition to language - by changing colour across a rich field of hues. This doesn't try to make a direct analogy to our emotions and in that sense makes the problem clearer as, in a sense, a clustering of internal states.
Global Wealth Redistribution to Mitigate Arms Races
Is it irrational for North Korea to try and build nuclear weapons? Maybe. However if your country is disenfranchised and in poverty, it does seem like one route to having a say in global affairs and a better life. There are certainly other routes, and South Korea offers an example of what countries can achieve. However, as the world does not have a version of a 'safety net' for poor countries, there remains some incentive to race for power. In other words: if you are not confident that those in power are looking out for your interests, it might make sense to start seeking power through... (read more)